You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by ha...@apache.org on 2018/07/30 22:36:35 UTC
[2/3] hive git commit: HIVE-20210 : Simple Fetch optimizer should
lead to MapReduce when filter on non-partition column and conversion is
minimal (Jeffery Yan via Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/65f02d2f/ql/src/test/results/clientpositive/list_bucket_dml_13.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_13.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_13.q.out
index a43a0b7..b9f658a 100644
--- a/ql/src/test/results/clientpositive/list_bucket_dml_13.q.out
+++ b/ql/src/test/results/clientpositive/list_bucket_dml_13.q.out
@@ -298,14 +298,55 @@ OPTIMIZED SQL: SELECT `col1`, CAST('466' AS STRING) AS `col2`, `col3`, CAST('val
FROM `default`.`list_bucketing_mul_col`
WHERE `ds` = '2008-04-08' AND `hr` = '2013-01-23+18:00:99' AND `col2` = '466' AND `col4` = 'val_466'
STAGE DEPENDENCIES:
- Stage-0 is a root stage
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Partition Description:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: list_bucketing_mul_col
+ filterExpr: ((col2 = '466') and (col4 = 'val_466')) (type: boolean)
+ Statistics: Num rows: 500 Data size: 6312 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: ((col2 = '466') and (col4 = 'val_466')) (type: boolean)
+ Statistics: Num rows: 125 Data size: 1578 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: col1 (type: string), '466' (type: string), col3 (type: string), 'val_466' (type: string), col5 (type: string), '2008-04-08' (type: string), '2013-01-23+18:00:99' (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
+ Statistics: Num rows: 125 Data size: 1578 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 125 Data size: 1578 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2,_col3,_col4,_col5,_col6
+ columns.types string:string:string:string:string:string:string
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.escape.crlf true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+ Execution mode: vectorized
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
Partition
+ base file name: col4=val_466
input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
partition values:
@@ -352,21 +393,14 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
name: default.list_bucketing_mul_col
name: default.list_bucketing_mul_col
+ Truncated Path -> Alias:
+ /list_bucketing_mul_col/ds=2008-04-08/hr=2013-01-23+18%3A00%3A99/col2=466/col4=val_466 [list_bucketing_mul_col]
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
Processor Tree:
- TableScan
- alias: list_bucketing_mul_col
- filterExpr: ((col2 = '466') and (col4 = 'val_466')) (type: boolean)
- Statistics: Num rows: 500 Data size: 6312 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((col2 = '466') and (col4 = 'val_466')) (type: boolean)
- Statistics: Num rows: 125 Data size: 1578 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: col1 (type: string), '466' (type: string), col3 (type: string), 'val_466' (type: string), col5 (type: string), '2008-04-08' (type: string), '2013-01-23+18:00:99' (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
- Statistics: Num rows: 125 Data size: 1578 Basic stats: COMPLETE Column stats: NONE
- ListSink
+ ListSink
PREHOOK: query: select * from list_bucketing_mul_col
where ds='2008-04-08' and hr='2013-01-23+18:00:99' and col2 = "466" and col4 = "val_466"
http://git-wip-us.apache.org/repos/asf/hive/blob/65f02d2f/ql/src/test/results/clientpositive/list_bucket_dml_2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_2.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_2.q.out
index 5750fdd..bd8e215 100644
--- a/ql/src/test/results/clientpositive/list_bucket_dml_2.q.out
+++ b/ql/src/test/results/clientpositive/list_bucket_dml_2.q.out
@@ -365,14 +365,55 @@ OPTIMIZED SQL: SELECT CAST('484' AS STRING) AS `key`, CAST('val_484' AS STRING)
FROM `default`.`list_bucketing_static_part_n4`
WHERE `ds` = '2008-04-08' AND `hr` = '11' AND `key` = '484' AND `value` = 'val_484'
STAGE DEPENDENCIES:
- Stage-0 is a root stage
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Partition Description:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: list_bucketing_static_part_n4
+ filterExpr: ((key = '484') and (value = 'val_484')) (type: boolean)
+ Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: ((key = '484') and (value = 'val_484')) (type: boolean)
+ Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: '484' (type: string), 'val_484' (type: string), '2008-04-08' (type: string), '11' (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2,_col3
+ columns.types string:string:string:string
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.escape.crlf true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+ Execution mode: vectorized
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
Partition
+ base file name: value=val_484
input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
partition values:
@@ -419,21 +460,14 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
name: default.list_bucketing_static_part_n4
name: default.list_bucketing_static_part_n4
+ Truncated Path -> Alias:
+ /list_bucketing_static_part_n4/ds=2008-04-08/hr=11/key=484/value=val_484 [list_bucketing_static_part_n4]
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
Processor Tree:
- TableScan
- alias: list_bucketing_static_part_n4
- filterExpr: ((key = '484') and (value = 'val_484')) (type: boolean)
- Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((key = '484') and (value = 'val_484')) (type: boolean)
- Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: '484' (type: string), 'val_484' (type: string), '2008-04-08' (type: string), '11' (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
- ListSink
+ ListSink
PREHOOK: query: select * from list_bucketing_static_part_n4 where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
PREHOOK: type: QUERY
http://git-wip-us.apache.org/repos/asf/hive/blob/65f02d2f/ql/src/test/results/clientpositive/list_bucket_dml_3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_3.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_3.q.out
index affbdf5..5ba8948 100644
--- a/ql/src/test/results/clientpositive/list_bucket_dml_3.q.out
+++ b/ql/src/test/results/clientpositive/list_bucket_dml_3.q.out
@@ -357,14 +357,55 @@ OPTIMIZED SQL: SELECT CAST('484' AS STRING) AS `key`, `value`
FROM `default`.`list_bucketing_static_part_n1`
WHERE `ds` = '2008-04-08' AND `hr` = '11' AND `key` = '484'
STAGE DEPENDENCIES:
- Stage-0 is a root stage
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Partition Description:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: list_bucketing_static_part_n1
+ filterExpr: ((ds = '2008-04-08') and (hr = '11') and (key = '484')) (type: boolean)
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: (key = '484') (type: boolean)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: '484' (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1
+ columns.types string:string
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.escape.crlf true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+ Execution mode: vectorized
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
Partition
+ base file name: key=484
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
partition values:
@@ -411,21 +452,14 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.list_bucketing_static_part_n1
name: default.list_bucketing_static_part_n1
+ Truncated Path -> Alias:
+ /list_bucketing_static_part_n1/ds=2008-04-08/hr=11/key=484 [list_bucketing_static_part_n1]
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
Processor Tree:
- TableScan
- alias: list_bucketing_static_part_n1
- filterExpr: ((ds = '2008-04-08') and (hr = '11') and (key = '484')) (type: boolean)
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: (key = '484') (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: '484' (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- ListSink
+ ListSink
PREHOOK: query: select key, value from list_bucketing_static_part_n1 where ds='2008-04-08' and hr='11' and key = "484"
PREHOOK: type: QUERY
http://git-wip-us.apache.org/repos/asf/hive/blob/65f02d2f/ql/src/test/results/clientpositive/list_bucket_dml_4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_4.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_4.q.out
index 4ddd112..520d48e 100644
--- a/ql/src/test/results/clientpositive/list_bucket_dml_4.q.out
+++ b/ql/src/test/results/clientpositive/list_bucket_dml_4.q.out
@@ -808,14 +808,55 @@ OPTIMIZED SQL: SELECT CAST('484' AS STRING) AS `key`, CAST('val_484' AS STRING)
FROM `default`.`list_bucketing_static_part_n2`
WHERE `ds` = '2008-04-08' AND `hr` = '11' AND `key` = '484' AND `value` = 'val_484'
STAGE DEPENDENCIES:
- Stage-0 is a root stage
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Partition Description:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: list_bucketing_static_part_n2
+ filterExpr: ((key = '484') and (value = 'val_484')) (type: boolean)
+ Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: ((key = '484') and (value = 'val_484')) (type: boolean)
+ Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: '484' (type: string), 'val_484' (type: string), '2008-04-08' (type: string), '11' (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2,_col3
+ columns.types string:string:string:string
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.escape.crlf true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+ Execution mode: vectorized
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
Partition
+ base file name: value=val_484
input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
partition values:
@@ -862,21 +903,14 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
name: default.list_bucketing_static_part_n2
name: default.list_bucketing_static_part_n2
+ Truncated Path -> Alias:
+ /list_bucketing_static_part_n2/ds=2008-04-08/hr=11/key=484/value=val_484 [list_bucketing_static_part_n2]
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
Processor Tree:
- TableScan
- alias: list_bucketing_static_part_n2
- filterExpr: ((key = '484') and (value = 'val_484')) (type: boolean)
- Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((key = '484') and (value = 'val_484')) (type: boolean)
- Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: '484' (type: string), 'val_484' (type: string), '2008-04-08' (type: string), '11' (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
- ListSink
+ ListSink
PREHOOK: query: select * from list_bucketing_static_part_n2 where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
PREHOOK: type: QUERY
http://git-wip-us.apache.org/repos/asf/hive/blob/65f02d2f/ql/src/test/results/clientpositive/list_bucket_dml_5.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_5.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_5.q.out
index 06e2a45..47c9e24 100644
--- a/ql/src/test/results/clientpositive/list_bucket_dml_5.q.out
+++ b/ql/src/test/results/clientpositive/list_bucket_dml_5.q.out
@@ -414,14 +414,55 @@ OPTIMIZED SQL: SELECT CAST('103' AS STRING) AS `key`, CAST('val_103' AS STRING)
FROM `default`.`list_bucketing_dynamic_part_n1`
WHERE `ds` = '2008-04-08' AND `key` = '103' AND `value` = 'val_103'
STAGE DEPENDENCIES:
- Stage-0 is a root stage
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Partition Description:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: list_bucketing_dynamic_part_n1
+ filterExpr: ((key = '103') and (value = 'val_103')) (type: boolean)
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: ((key = '103') and (value = 'val_103')) (type: boolean)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: '103' (type: string), 'val_103' (type: string), '2008-04-08' (type: string), hr (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2,_col3
+ columns.types string:string:string:string
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.escape.crlf true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+ Execution mode: vectorized
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
Partition
+ base file name: value=val_103
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
partition values:
@@ -468,7 +509,9 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.list_bucketing_dynamic_part_n1
name: default.list_bucketing_dynamic_part_n1
+#### A masked pattern was here ####
Partition
+ base file name: value=val_103
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
partition values:
@@ -515,21 +558,15 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.list_bucketing_dynamic_part_n1
name: default.list_bucketing_dynamic_part_n1
+ Truncated Path -> Alias:
+ /list_bucketing_dynamic_part_n1/ds=2008-04-08/hr=11/key=103/value=val_103 [list_bucketing_dynamic_part_n1]
+ /list_bucketing_dynamic_part_n1/ds=2008-04-08/hr=12/key=103/value=val_103 [list_bucketing_dynamic_part_n1]
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
Processor Tree:
- TableScan
- alias: list_bucketing_dynamic_part_n1
- filterExpr: ((key = '103') and (value = 'val_103')) (type: boolean)
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((key = '103') and (value = 'val_103')) (type: boolean)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: '103' (type: string), 'val_103' (type: string), '2008-04-08' (type: string), hr (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- ListSink
+ ListSink
PREHOOK: query: select key, value, ds, hr from list_bucketing_dynamic_part_n1 where ds='2008-04-08' and key = "103" and value ="val_103"
PREHOOK: type: QUERY
http://git-wip-us.apache.org/repos/asf/hive/blob/65f02d2f/ql/src/test/results/clientpositive/list_bucket_dml_6.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_6.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_6.q.out
index a3089a7..aad1458 100644
--- a/ql/src/test/results/clientpositive/list_bucket_dml_6.q.out
+++ b/ql/src/test/results/clientpositive/list_bucket_dml_6.q.out
@@ -904,14 +904,55 @@ OPTIMIZED SQL: SELECT CAST('484' AS STRING) AS `key`, CAST('val_484' AS STRING)
FROM `default`.`list_bucketing_dynamic_part_n3`
WHERE `key` = '484' AND `value` = 'val_484'
STAGE DEPENDENCIES:
- Stage-0 is a root stage
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Partition Description:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: list_bucketing_dynamic_part_n3
+ filterExpr: ((key = '484') and (value = 'val_484')) (type: boolean)
+ Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: ((key = '484') and (value = 'val_484')) (type: boolean)
+ Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: '484' (type: string), 'val_484' (type: string), ds (type: string), hr (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2,_col3
+ columns.types string:string:string:string
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.escape.crlf true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+ Execution mode: vectorized
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
Partition
+ base file name: hr=a1
input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
partition values:
@@ -958,7 +999,9 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
name: default.list_bucketing_dynamic_part_n3
name: default.list_bucketing_dynamic_part_n3
+#### A masked pattern was here ####
Partition
+ base file name: value=val_484
input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
partition values:
@@ -1005,21 +1048,15 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
name: default.list_bucketing_dynamic_part_n3
name: default.list_bucketing_dynamic_part_n3
+ Truncated Path -> Alias:
+ /list_bucketing_dynamic_part_n3/ds=2008-04-08/hr=a1 [list_bucketing_dynamic_part_n3]
+ /list_bucketing_dynamic_part_n3/ds=2008-04-08/hr=b1/key=484/value=val_484 [list_bucketing_dynamic_part_n3]
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
Processor Tree:
- TableScan
- alias: list_bucketing_dynamic_part_n3
- filterExpr: ((key = '484') and (value = 'val_484')) (type: boolean)
- Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((key = '484') and (value = 'val_484')) (type: boolean)
- Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: '484' (type: string), 'val_484' (type: string), ds (type: string), hr (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
- ListSink
+ ListSink
PREHOOK: query: select * from list_bucketing_dynamic_part_n3 where key = '484' and value = 'val_484'
PREHOOK: type: QUERY
http://git-wip-us.apache.org/repos/asf/hive/blob/65f02d2f/ql/src/test/results/clientpositive/list_bucket_dml_7.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_7.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_7.q.out
index faef7a9..7232e79 100644
--- a/ql/src/test/results/clientpositive/list_bucket_dml_7.q.out
+++ b/ql/src/test/results/clientpositive/list_bucket_dml_7.q.out
@@ -904,14 +904,55 @@ OPTIMIZED SQL: SELECT CAST('484' AS STRING) AS `key`, CAST('val_484' AS STRING)
FROM `default`.`list_bucketing_dynamic_part`
WHERE `key` = '484' AND `value` = 'val_484'
STAGE DEPENDENCIES:
- Stage-0 is a root stage
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Partition Description:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: list_bucketing_dynamic_part
+ filterExpr: ((key = '484') and (value = 'val_484')) (type: boolean)
+ Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: ((key = '484') and (value = 'val_484')) (type: boolean)
+ Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: '484' (type: string), 'val_484' (type: string), ds (type: string), hr (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2,_col3
+ columns.types string:string:string:string
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.escape.crlf true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+ Execution mode: vectorized
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
Partition
+ base file name: hr=a1
input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
partition values:
@@ -958,7 +999,9 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
name: default.list_bucketing_dynamic_part
name: default.list_bucketing_dynamic_part
+#### A masked pattern was here ####
Partition
+ base file name: hr=b1
input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
partition values:
@@ -1005,21 +1048,15 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
name: default.list_bucketing_dynamic_part
name: default.list_bucketing_dynamic_part
+ Truncated Path -> Alias:
+ /list_bucketing_dynamic_part/ds=2008-04-08/hr=a1 [list_bucketing_dynamic_part]
+ /list_bucketing_dynamic_part/ds=2008-04-08/hr=b1 [list_bucketing_dynamic_part]
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
Processor Tree:
- TableScan
- alias: list_bucketing_dynamic_part
- filterExpr: ((key = '484') and (value = 'val_484')) (type: boolean)
- Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((key = '484') and (value = 'val_484')) (type: boolean)
- Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: '484' (type: string), 'val_484' (type: string), ds (type: string), hr (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
- ListSink
+ ListSink
PREHOOK: query: select * from list_bucketing_dynamic_part where key = '484' and value = 'val_484'
PREHOOK: type: QUERY
http://git-wip-us.apache.org/repos/asf/hive/blob/65f02d2f/ql/src/test/results/clientpositive/list_bucket_dml_8.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_8.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_8.q.out
index eac6407..337f9dc 100644
--- a/ql/src/test/results/clientpositive/list_bucket_dml_8.q.out
+++ b/ql/src/test/results/clientpositive/list_bucket_dml_8.q.out
@@ -464,14 +464,55 @@ OPTIMIZED SQL: SELECT CAST('484' AS STRING) AS `key`, CAST('val_484' AS STRING)
FROM `default`.`list_bucketing_dynamic_part_n2`
WHERE `key` = '484' AND `value` = 'val_484'
STAGE DEPENDENCIES:
- Stage-0 is a root stage
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Partition Description:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: list_bucketing_dynamic_part_n2
+ filterExpr: ((key = '484') and (value = 'val_484')) (type: boolean)
+ Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: ((key = '484') and (value = 'val_484')) (type: boolean)
+ Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: '484' (type: string), 'val_484' (type: string), ds (type: string), hr (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2,_col3
+ columns.types string:string:string:string
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.escape.crlf true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+ Execution mode: vectorized
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
Partition
+ base file name: hr=a1
input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
partition values:
@@ -518,7 +559,9 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
name: default.list_bucketing_dynamic_part_n2
name: default.list_bucketing_dynamic_part_n2
+#### A masked pattern was here ####
Partition
+ base file name: hr=b1
input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
partition values:
@@ -564,21 +607,15 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
name: default.list_bucketing_dynamic_part_n2
name: default.list_bucketing_dynamic_part_n2
+ Truncated Path -> Alias:
+ /list_bucketing_dynamic_part_n2/ds=2008-04-08/hr=a1 [list_bucketing_dynamic_part_n2]
+ /list_bucketing_dynamic_part_n2/ds=2008-04-08/hr=b1 [list_bucketing_dynamic_part_n2]
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
Processor Tree:
- TableScan
- alias: list_bucketing_dynamic_part_n2
- filterExpr: ((key = '484') and (value = 'val_484')) (type: boolean)
- Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((key = '484') and (value = 'val_484')) (type: boolean)
- Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: '484' (type: string), 'val_484' (type: string), ds (type: string), hr (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
- ListSink
+ ListSink
PREHOOK: query: select * from list_bucketing_dynamic_part_n2 where key = '484' and value = 'val_484'
PREHOOK: type: QUERY
http://git-wip-us.apache.org/repos/asf/hive/blob/65f02d2f/ql/src/test/results/clientpositive/list_bucket_dml_9.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_9.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_9.q.out
index 1e1fc13..fbd4fde 100644
--- a/ql/src/test/results/clientpositive/list_bucket_dml_9.q.out
+++ b/ql/src/test/results/clientpositive/list_bucket_dml_9.q.out
@@ -808,14 +808,55 @@ OPTIMIZED SQL: SELECT CAST('484' AS STRING) AS `key`, CAST('val_484' AS STRING)
FROM `default`.`list_bucketing_static_part_n0`
WHERE `ds` = '2008-04-08' AND `hr` = '11' AND `key` = '484' AND `value` = 'val_484'
STAGE DEPENDENCIES:
- Stage-0 is a root stage
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Partition Description:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: list_bucketing_static_part_n0
+ filterExpr: ((key = '484') and (value = 'val_484')) (type: boolean)
+ Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: ((key = '484') and (value = 'val_484')) (type: boolean)
+ Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: '484' (type: string), 'val_484' (type: string), '2008-04-08' (type: string), '11' (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2,_col3
+ columns.types string:string:string:string
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.escape.crlf true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+ Execution mode: vectorized
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
Partition
+ base file name: key=484
input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
partition values:
@@ -862,21 +903,14 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
name: default.list_bucketing_static_part_n0
name: default.list_bucketing_static_part_n0
+ Truncated Path -> Alias:
+ /list_bucketing_static_part_n0/ds=2008-04-08/hr=11/key=484 [list_bucketing_static_part_n0]
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
Processor Tree:
- TableScan
- alias: list_bucketing_static_part_n0
- filterExpr: ((key = '484') and (value = 'val_484')) (type: boolean)
- Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((key = '484') and (value = 'val_484')) (type: boolean)
- Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: '484' (type: string), 'val_484' (type: string), '2008-04-08' (type: string), '11' (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
- ListSink
+ ListSink
PREHOOK: query: select * from list_bucketing_static_part_n0 where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
PREHOOK: type: QUERY
http://git-wip-us.apache.org/repos/asf/hive/blob/65f02d2f/ql/src/test/results/clientpositive/list_bucket_query_multiskew_1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_query_multiskew_1.q.out b/ql/src/test/results/clientpositive/list_bucket_query_multiskew_1.q.out
index a09e007..e324cab 100644
--- a/ql/src/test/results/clientpositive/list_bucket_query_multiskew_1.q.out
+++ b/ql/src/test/results/clientpositive/list_bucket_query_multiskew_1.q.out
@@ -84,14 +84,55 @@ OPTIMIZED SQL: SELECT CAST('484' AS STRING) AS `key`
FROM `default`.`fact_daily`
WHERE `ds` = '1' AND `hr` = '4' AND `key` = '484' AND `value` = 'val_484'
STAGE DEPENDENCIES:
- Stage-0 is a root stage
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Partition Description:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: fact_daily
+ filterExpr: ((key = '484') and (value = 'val_484')) (type: boolean)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: ((key = '484') and (value = 'val_484')) (type: boolean)
+ Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: '484' (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0
+ columns.types string
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.escape.crlf true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+ Execution mode: vectorized
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
Partition
+ base file name: value=val_484
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
partition values:
@@ -138,21 +179,14 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.fact_daily
name: default.fact_daily
+ Truncated Path -> Alias:
+ /fact_daily/ds=1/hr=4/key=484/value=val_484 [fact_daily]
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
Processor Tree:
- TableScan
- alias: fact_daily
- filterExpr: ((key = '484') and (value = 'val_484')) (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((key = '484') and (value = 'val_484')) (type: boolean)
- Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: '484' (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
- ListSink
+ ListSink
PREHOOK: query: SELECT key FROM fact_daily WHERE ( ds='1' and hr='4') and (key='484' and value= 'val_484')
PREHOOK: type: QUERY
@@ -173,14 +207,55 @@ OPTIMIZED SQL: SELECT CAST('238' AS STRING) AS `key`, CAST('val_238' AS STRING)
FROM `default`.`fact_daily`
WHERE `ds` = '1' AND `hr` = '4' AND `key` = '238' AND `value` = 'val_238'
STAGE DEPENDENCIES:
- Stage-0 is a root stage
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Partition Description:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: fact_daily
+ filterExpr: ((key = '238') and (value = 'val_238')) (type: boolean)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: ((key = '238') and (value = 'val_238')) (type: boolean)
+ Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: '238' (type: string), 'val_238' (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1
+ columns.types string:string
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.escape.crlf true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+ Execution mode: vectorized
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
Partition
+ base file name: value=val_238
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
partition values:
@@ -227,21 +302,14 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.fact_daily
name: default.fact_daily
+ Truncated Path -> Alias:
+ /fact_daily/ds=1/hr=4/key=238/value=val_238 [fact_daily]
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
Processor Tree:
- TableScan
- alias: fact_daily
- filterExpr: ((key = '238') and (value = 'val_238')) (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((key = '238') and (value = 'val_238')) (type: boolean)
- Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: '238' (type: string), 'val_238' (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
- ListSink
+ ListSink
PREHOOK: query: SELECT key,value FROM fact_daily WHERE ( ds='1' and hr='4') and (key='238' and value= 'val_238')
PREHOOK: type: QUERY
@@ -263,14 +331,55 @@ OPTIMIZED SQL: SELECT `key`
FROM `default`.`fact_daily`
WHERE `ds` = '1' AND `hr` = '4' AND `value` = '3'
STAGE DEPENDENCIES:
- Stage-0 is a root stage
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Partition Description:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: fact_daily
+ filterExpr: ((ds = '1') and (hr = '4') and (value = '3')) (type: boolean)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: (value = '3') (type: boolean)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0
+ columns.types string
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.escape.crlf true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+ Execution mode: vectorized
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
Partition
+ base file name: HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
partition values:
@@ -317,21 +426,14 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.fact_daily
name: default.fact_daily
+ Truncated Path -> Alias:
+ /fact_daily/ds=1/hr=4/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME [fact_daily]
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
Processor Tree:
- TableScan
- alias: fact_daily
- filterExpr: ((ds = '1') and (hr = '4') and (value = '3')) (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: (value = '3') (type: boolean)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- ListSink
+ ListSink
PREHOOK: query: SELECT key FROM fact_daily WHERE ( ds='1' and hr='4') and (value = "3")
PREHOOK: type: QUERY
@@ -351,14 +453,55 @@ OPTIMIZED SQL: SELECT CAST('495' AS STRING) AS `key`, `value`
FROM `default`.`fact_daily`
WHERE `ds` = '1' AND `hr` = '4' AND `key` = '495'
STAGE DEPENDENCIES:
- Stage-0 is a root stage
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Partition Description:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: fact_daily
+ filterExpr: ((ds = '1') and (hr = '4') and (key = '495')) (type: boolean)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: (key = '495') (type: boolean)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: '495' (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1
+ columns.types string:string
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.escape.crlf true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+ Execution mode: vectorized
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
Partition
+ base file name: HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
partition values:
@@ -405,21 +548,14 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.fact_daily
name: default.fact_daily
+ Truncated Path -> Alias:
+ /fact_daily/ds=1/hr=4/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME [fact_daily]
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
Processor Tree:
- TableScan
- alias: fact_daily
- filterExpr: ((ds = '1') and (hr = '4') and (key = '495')) (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: (key = '495') (type: boolean)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: '495' (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- ListSink
+ ListSink
PREHOOK: query: SELECT key,value FROM fact_daily WHERE ( ds='1' and hr='4') and key = '369'
PREHOOK: type: QUERY
http://git-wip-us.apache.org/repos/asf/hive/blob/65f02d2f/ql/src/test/results/clientpositive/list_bucket_query_multiskew_2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_query_multiskew_2.q.out b/ql/src/test/results/clientpositive/list_bucket_query_multiskew_2.q.out
index 6217adb..98ad365 100644
--- a/ql/src/test/results/clientpositive/list_bucket_query_multiskew_2.q.out
+++ b/ql/src/test/results/clientpositive/list_bucket_query_multiskew_2.q.out
@@ -84,14 +84,104 @@ OPTIMIZED SQL: SELECT `key`, CAST('val_484' AS STRING) AS `value`
FROM `default`.`fact_daily_n2`
WHERE `ds` = '1' AND `hr` = '4' AND `value` = 'val_484'
STAGE DEPENDENCIES:
- Stage-0 is a root stage
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Partition Description:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: fact_daily_n2
+ filterExpr: ((ds = '1') and (hr = '4') and (value = 'val_484')) (type: boolean)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: (value = 'val_484') (type: boolean)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), 'val_484' (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1
+ columns.types string:string
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.escape.crlf true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+ Execution mode: vectorized
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 1
+ hr 4
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.fact_daily_n2
+ numFiles 3
+ numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 5312
+ serialization.ddl struct fact_daily_n2 { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ bucketing_version 2
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.fact_daily_n2
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct fact_daily_n2 { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.fact_daily_n2
+ name: default.fact_daily_n2
+#### A masked pattern was here ####
Partition
+ base file name: value=val_484
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
partition values:
@@ -138,21 +228,15 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.fact_daily_n2
name: default.fact_daily_n2
+ Truncated Path -> Alias:
+ /fact_daily_n2/ds=1/hr=4/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME [fact_daily_n2]
+ /fact_daily_n2/ds=1/hr=4/key=484/value=val_484 [fact_daily_n2]
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
Processor Tree:
- TableScan
- alias: fact_daily_n2
- filterExpr: ((ds = '1') and (hr = '4') and (value = 'val_484')) (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: (value = 'val_484') (type: boolean)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), 'val_484' (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- ListSink
+ ListSink
PREHOOK: query: SELECT key, value FROM fact_daily_n2 WHERE ds='1' and hr='4' and value= 'val_484'
PREHOOK: type: QUERY
@@ -173,14 +257,55 @@ OPTIMIZED SQL: SELECT CAST('406' AS STRING) AS `key`
FROM `default`.`fact_daily_n2`
WHERE `ds` = '1' AND `hr` = '4' AND `key` = '406'
STAGE DEPENDENCIES:
- Stage-0 is a root stage
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Partition Description:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: fact_daily_n2
+ filterExpr: ((ds = '1') and (hr = '4') and (key = '406')) (type: boolean)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: (key = '406') (type: boolean)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: '406' (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0
+ columns.types string
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.escape.crlf true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+ Execution mode: vectorized
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
Partition
+ base file name: HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
partition values:
@@ -227,21 +352,14 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.fact_daily_n2
name: default.fact_daily_n2
+ Truncated Path -> Alias:
+ /fact_daily_n2/ds=1/hr=4/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME [fact_daily_n2]
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
Processor Tree:
- TableScan
- alias: fact_daily_n2
- filterExpr: ((ds = '1') and (hr = '4') and (key = '406')) (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: (key = '406') (type: boolean)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: '406' (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- ListSink
+ ListSink
PREHOOK: query: SELECT key, value FROM fact_daily_n2 WHERE ds='1' and hr='4' and key= '406'
PREHOOK: type: QUERY
@@ -265,14 +383,55 @@ OPTIMIZED SQL: SELECT `key`, `value`
FROM `default`.`fact_daily_n2`
WHERE `ds` = '1' AND `hr` = '4' AND (`key` = '484' AND `value` = 'val_484' OR `key` = '238' AND `value` = 'val_238')
STAGE DEPENDENCIES:
- Stage-0 is a root stage
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Partition Description:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: fact_daily_n2
+ filterExpr: ((ds = '1') and (hr = '4') and (((key = '484') and (value = 'val_484')) or ((key = '238') and (value = 'val_238')))) (type: boolean)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: (((key = '238') and (value = 'val_238')) or ((key = '484') and (value = 'val_484'))) (type: boolean)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1
+ columns.types string:string
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.escape.crlf true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+ Execution mode: vectorized
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
Partition
+ base file name: value=val_238
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
partition values:
@@ -319,21 +478,64 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.fact_daily_n2
name: default.fact_daily_n2
+#### A masked pattern was here ####
+ Partition
+ base file name: value=val_484
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 1
+ hr 4
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.fact_daily_n2
+ numFiles 3
+ numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 5312
+ serialization.ddl struct fact_daily_n2 { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ bucketing_version 2
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.fact_daily_n2
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct fact_daily_n2 { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.fact_daily_n2
+ name: default.fact_daily_n2
+ Truncated Path -> Alias:
+ /fact_daily_n2/ds=1/hr=4/key=238/value=val_238 [fact_daily_n2]
+ /fact_daily_n2/ds=1/hr=4/key=484/value=val_484 [fact_daily_n2]
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
Processor Tree:
- TableScan
- alias: fact_daily_n2
- filterExpr: ((ds = '1') and (hr = '4') and (((key = '484') and (value = 'val_484')) or ((key = '238') and (value = 'val_238')))) (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: (((key = '238') and (value = 'val_238')) or ((key = '484') and (value = 'val_484'))) (type: boolean)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- ListSink
+ ListSink
PREHOOK: query: SELECT key, value FROM fact_daily_n2 WHERE ds='1' and hr='4' and ( (key='484' and value ='val_484') or (key='238' and value= 'val_238'))
PREHOOK: type: QUERY