blob: c3f8d78845c261119432a2f7a58564a6a5416d7d [file] [log] [blame]
PREHOOK: query: create table MY_TABLE_0001 (
col_1 string,
col_3 timestamp,
col_7 string,
col_20 string)
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@MY_TABLE_0001
POSTHOOK: query: create table MY_TABLE_0001 (
col_1 string,
col_3 timestamp,
col_7 string,
col_20 string)
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@MY_TABLE_0001
PREHOOK: query: create table MY_TABLE_0001_00 (
col_1 string,
col_22 string,
col_23 int)
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@MY_TABLE_0001_00
POSTHOOK: query: create table MY_TABLE_0001_00 (
col_1 string,
col_22 string,
col_23 int)
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@MY_TABLE_0001_00
PREHOOK: query: create table MY_TABLE_0003 (
col_24 string,
col_21 string)
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@MY_TABLE_0003
POSTHOOK: query: create table MY_TABLE_0003 (
col_24 string,
col_21 string)
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@MY_TABLE_0003
PREHOOK: query: create table MY_TABLE_0001_01 (
col_1 string,
col_100 string)
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@MY_TABLE_0001_01
POSTHOOK: query: create table MY_TABLE_0001_01 (
col_1 string,
col_100 string)
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@MY_TABLE_0001_01
PREHOOK: query: explain extended SELECT
Table__323.col_7,
CAST(Table__323.col_3 AS DATE) col_3,
Table__323.col_20,
Table__1232.col_21 col_21_1232,
Table__323.col_1,
Table__133.col_22,
Table__879.col_21 col_21_879
,Table__133.col_23
FROM MY_TABLE_0001 Table__323
LEFT OUTER JOIN MY_TABLE_0003 Table__1232 ON (Table__323.col_20=Table__1232.col_24)
LEFT OUTER JOIN MY_TABLE_0001_00 Table__133 ON (Table__323.col_1=Table__133.col_1)
LEFT OUTER JOIN MY_TABLE_0003 Table__879 ON (Table__133.col_22=Table__879.col_24)
LEFT OUTER JOIN MY_TABLE_0001_01 Table__1215 ON (Table__323.col_1=Table__1215.col_1 and Table__1215.col_100 = 210)
WHERE 1=1
AND (cast(Table__323.col_7 AS DOUBLE) IS NOT NULL OR Table__323.col_7 IS NULL)
AND CAST(Table__323.col_3 AS DATE) BETWEEN '2018-07-01' AND '2019-01-23'
AND Table__323.col_20 IN ('part1','part2','part3')
PREHOOK: type: QUERY
PREHOOK: Input: default@my_table_0001
PREHOOK: Input: default@my_table_0001_00
PREHOOK: Input: default@my_table_0001_01
PREHOOK: Input: default@my_table_0003
#### A masked pattern was here ####
POSTHOOK: query: explain extended SELECT
Table__323.col_7,
CAST(Table__323.col_3 AS DATE) col_3,
Table__323.col_20,
Table__1232.col_21 col_21_1232,
Table__323.col_1,
Table__133.col_22,
Table__879.col_21 col_21_879
,Table__133.col_23
FROM MY_TABLE_0001 Table__323
LEFT OUTER JOIN MY_TABLE_0003 Table__1232 ON (Table__323.col_20=Table__1232.col_24)
LEFT OUTER JOIN MY_TABLE_0001_00 Table__133 ON (Table__323.col_1=Table__133.col_1)
LEFT OUTER JOIN MY_TABLE_0003 Table__879 ON (Table__133.col_22=Table__879.col_24)
LEFT OUTER JOIN MY_TABLE_0001_01 Table__1215 ON (Table__323.col_1=Table__1215.col_1 and Table__1215.col_100 = 210)
WHERE 1=1
AND (cast(Table__323.col_7 AS DOUBLE) IS NOT NULL OR Table__323.col_7 IS NULL)
AND CAST(Table__323.col_3 AS DATE) BETWEEN '2018-07-01' AND '2019-01-23'
AND Table__323.col_20 IN ('part1','part2','part3')
POSTHOOK: type: QUERY
POSTHOOK: Input: default@my_table_0001
POSTHOOK: Input: default@my_table_0001_00
POSTHOOK: Input: default@my_table_0001_01
POSTHOOK: Input: default@my_table_0003
#### A masked pattern was here ####
OPTIMIZED SQL: SELECT `t0`.`col_7`, `t0`.`CAST` AS `col_3`, `t0`.`col_20`, `t2`.`col_21` AS `col_21_1232`, `t0`.`col_1`, `t4`.`col_22`, `t6`.`col_21` AS `col_21_879`, `t4`.`col_23`
FROM (SELECT `col_1`, `col_7`, `col_20`, CAST(`col_3` AS DATE) AS `CAST`
FROM `default`.`my_table_0001`
WHERE (CAST(`col_7` AS DOUBLE) IS NOT NULL OR `col_7` IS NULL) AND `col_20` IN ('part1', 'part2', 'part3') AND CAST(`col_3` AS DATE) BETWEEN DATE '2018-07-01' AND DATE '2019-01-23') AS `t0`
LEFT JOIN (SELECT `col_24`, `col_21`
FROM `default`.`my_table_0003`
WHERE `col_24` IN ('part1', 'part2', 'part3')) AS `t2` ON `t0`.`col_20` = `t2`.`col_24`
LEFT JOIN (SELECT `col_1`, `col_22`, `col_23`
FROM `default`.`my_table_0001_00`
WHERE `col_1` IS NOT NULL) AS `t4` ON `t0`.`col_1` = `t4`.`col_1`
LEFT JOIN (SELECT `col_24`, `col_21`
FROM `default`.`my_table_0003`
WHERE `col_24` IS NOT NULL) AS `t6` ON `t4`.`col_22` = `t6`.`col_24`
LEFT JOIN (SELECT `col_1`
FROM `default`.`my_table_0001_01`
WHERE `col_100` = 210 AND `col_1` IS NOT NULL) AS `t8` ON `t0`.`col_1` = `t8`.`col_1`
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
STAGE PLANS:
Stage: Stage-1
Tez
#### A masked pattern was here ####
Edges:
Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE)
Reducer 3 <- Map 7 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
Reducer 4 <- Map 6 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE)
Reducer 5 <- Map 8 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
alias: table__323
filterExpr: ((UDFToDouble(col_7) is not null or col_7 is null) and (col_20) IN ('part1', 'part2', 'part3') and CAST( col_3 AS DATE) BETWEEN DATE'2018-07-01' AND DATE'2019-01-23') (type: boolean)
Statistics: Num rows: 1 Data size: 592 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: ((UDFToDouble(col_7) is not null or col_7 is null) and (col_20) IN ('part1', 'part2', 'part3') and CAST( col_3 AS DATE) BETWEEN DATE'2018-07-01' AND DATE'2019-01-23') (type: boolean)
Statistics: Num rows: 1 Data size: 592 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: col_1 (type: string), col_7 (type: string), col_20 (type: string), CAST( col_3 AS DATE) (type: date)
outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 1 Data size: 592 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
bucketingVersion: 2
key expressions: _col2 (type: string)
null sort order: z
numBuckets: -1
sort order: +
Map-reduce partition columns: _col2 (type: string)
Statistics: Num rows: 1 Data size: 592 Basic stats: COMPLETE Column stats: NONE
tag: 0
value expressions: _col0 (type: string), _col1 (type: string), _col3 (type: date)
auto parallelism: true
Execution mode: vectorized, llap
LLAP IO: all inputs
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
#### A masked pattern was here ####
Partition
base file name: my_table_0001
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 col_1,col_3,col_7,col_20
columns.types string:timestamp:string:string
#### A masked pattern was here ####
name default.my_table_0001
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
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:
bucketing_version 2
column.name.delimiter ,
columns col_1,col_3,col_7,col_20
columns.comments
columns.types string:timestamp:string:string
#### A masked pattern was here ####
name default.my_table_0001
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.my_table_0001
name: default.my_table_0001
Truncated Path -> Alias:
/my_table_0001 [table__323]
Map 6
Map Operator Tree:
TableScan
alias: table__1232
filterExpr: ((col_24) IN ('part1', 'part2', 'part3') or col_24 is not null) (type: boolean)
Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: (col_24) IN ('part1', 'part2', 'part3') (type: boolean)
Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: col_24 (type: string), col_21 (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
bucketingVersion: 2
key expressions: _col0 (type: string)
null sort order: z
numBuckets: -1
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
tag: 1
value expressions: _col1 (type: string)
auto parallelism: true
Filter Operator
isSamplingPred: false
predicate: col_24 is not null (type: boolean)
Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: col_24 (type: string), col_21 (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
bucketingVersion: 2
key expressions: _col0 (type: string)
null sort order: z
numBuckets: -1
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
tag: 1
value expressions: _col1 (type: string)
auto parallelism: true
Execution mode: vectorized, llap
LLAP IO: all inputs
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
#### A masked pattern was here ####
Partition
base file name: my_table_0003
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 col_24,col_21
columns.types string:string
#### A masked pattern was here ####
name default.my_table_0003
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
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:
bucketing_version 2
column.name.delimiter ,
columns col_24,col_21
columns.comments
columns.types string:string
#### A masked pattern was here ####
name default.my_table_0003
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.my_table_0003
name: default.my_table_0003
Truncated Path -> Alias:
/my_table_0003 [table__1232]
Map 7
Map Operator Tree:
TableScan
alias: table__133
filterExpr: col_1 is not null (type: boolean)
Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: col_1 is not null (type: boolean)
Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: col_1 (type: string), col_22 (type: string), col_23 (type: int)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
bucketingVersion: 2
key expressions: _col0 (type: string)
null sort order: z
numBuckets: -1
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE
tag: 1
value expressions: _col1 (type: string), _col2 (type: int)
auto parallelism: true
Execution mode: vectorized, llap
LLAP IO: all inputs
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
#### A masked pattern was here ####
Partition
base file name: my_table_0001_00
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 col_1,col_22,col_23
columns.types string:string:int
#### A masked pattern was here ####
name default.my_table_0001_00
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
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:
bucketing_version 2
column.name.delimiter ,
columns col_1,col_22,col_23
columns.comments
columns.types string:string:int
#### A masked pattern was here ####
name default.my_table_0001_00
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.my_table_0001_00
name: default.my_table_0001_00
Truncated Path -> Alias:
/my_table_0001_00 [table__133]
Map 8
Map Operator Tree:
TableScan
alias: table__1215
filterExpr: ((UDFToDouble(col_100) = 210.0D) and col_1 is not null) (type: boolean)
Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: ((UDFToDouble(col_100) = 210.0D) and col_1 is not null) (type: boolean)
Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: col_1 (type: string)
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
bucketingVersion: 2
key expressions: _col0 (type: string)
null sort order: z
numBuckets: -1
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
tag: 1
auto parallelism: true
Execution mode: vectorized, llap
LLAP IO: all inputs
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
#### A masked pattern was here ####
Partition
base file name: my_table_0001_01
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 col_1,col_100
columns.types string:string
#### A masked pattern was here ####
name default.my_table_0001_01
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
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:
bucketing_version 2
column.name.delimiter ,
columns col_1,col_100
columns.comments
columns.types string:string
#### A masked pattern was here ####
name default.my_table_0001_01
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.my_table_0001_01
name: default.my_table_0001_01
Truncated Path -> Alias:
/my_table_0001_01 [table__1215]
Reducer 2
Execution mode: llap
Needs Tagging: false
Reduce Operator Tree:
Merge Join Operator
condition map:
Left Outer Join 0 to 1
keys:
0 _col2 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col5
Position of Big Table: 0
Statistics: Num rows: 1 Data size: 651 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
bucketingVersion: 2
key expressions: _col0 (type: string)
null sort order: z
numBuckets: -1
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 1 Data size: 651 Basic stats: COMPLETE Column stats: NONE
tag: 0
value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: date), _col5 (type: string)
auto parallelism: true
Reducer 3
Execution mode: llap
Needs Tagging: false
Reduce Operator Tree:
Merge Join Operator
condition map:
Left Outer Join 0 to 1
keys:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col5, _col7, _col8
Position of Big Table: 0
Statistics: Num rows: 1 Data size: 716 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
bucketingVersion: 2
key expressions: _col7 (type: string)
null sort order: z
numBuckets: -1
sort order: +
Map-reduce partition columns: _col7 (type: string)
Statistics: Num rows: 1 Data size: 716 Basic stats: COMPLETE Column stats: NONE
tag: 0
value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: date), _col5 (type: string), _col8 (type: int)
auto parallelism: true
Reducer 4
Execution mode: llap
Needs Tagging: false
Reduce Operator Tree:
Merge Join Operator
condition map:
Left Outer Join 0 to 1
keys:
0 _col7 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col5, _col7, _col8, _col10
Position of Big Table: 0
Statistics: Num rows: 1 Data size: 787 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
bucketingVersion: 2
key expressions: _col0 (type: string)
null sort order: z
numBuckets: -1
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 1 Data size: 787 Basic stats: COMPLETE Column stats: NONE
tag: 0
value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: date), _col5 (type: string), _col7 (type: string), _col8 (type: int), _col10 (type: string)
auto parallelism: true
Reducer 5
Execution mode: llap
Needs Tagging: false
Reduce Operator Tree:
Merge Join Operator
condition map:
Left Outer Join 0 to 1
keys:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col5, _col7, _col8, _col10
Position of Big Table: 0
Statistics: Num rows: 1 Data size: 865 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col1 (type: string), _col3 (type: date), _col2 (type: string), _col5 (type: string), _col0 (type: string), _col7 (type: string), _col10 (type: string), _col8 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
Statistics: Num rows: 1 Data size: 865 Basic stats: COMPLETE Column stats: NONE
File Output Operator
bucketingVersion: 2
compressed: false
GlobalTableId: 0
#### A masked pattern was here ####
NumFilesPerFileSink: 1
Statistics: Num rows: 1 Data size: 865 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:
bucketing_version -1
columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7
columns.types string:date:string:string:string:string:string:int
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
Stage: Stage-0
Fetch Operator
limit: -1
Processor Tree:
ListSink
PREHOOK: query: explain extended
SELECT `t`.`p_name`
FROM (SELECT `p_name`, `p_type`, `p_size` + 1 AS `size`
FROM `part`) AS `t`
LEFT JOIN (SELECT `t5`.`size`, `t2`.`c`, `t2`.`ck`
FROM (SELECT `p_size` + 1 AS `+`, COUNT(*) AS `c`, COUNT(`p_type`) AS `ck`
FROM `part`
WHERE `p_size` IS NOT NULL
GROUP BY `p_size` + 1) AS `t2`
INNER JOIN (SELECT `p_size` + 1 AS `size`
FROM `part`
WHERE `p_size` IS NOT NULL
GROUP BY `p_size` + 1) AS `t5` ON `t2`.`+` = `t5`.`size`) AS `t6` ON `t`.`size` = `t6`.`size`
LEFT JOIN (SELECT `t9`.`p_type`, `t12`.`size`, TRUE AS `$f2`
FROM (SELECT `p_type`, `p_size` + 1 AS `+`
FROM `part`
WHERE `p_size` IS NOT NULL AND `p_type` IS NOT NULL
GROUP BY `p_type`, `p_size` + 1) AS `t9`
INNER JOIN (SELECT `p_size` + 1 AS `size`
FROM `part`
WHERE `p_size` IS NOT NULL
GROUP BY `p_size` + 1) AS `t12` ON `t9`.`+` = `t12`.`size`) AS `t14` ON `t`.`p_type` = `t14`.`p_type` AND `t`.`size` = `t14`.`size`
WHERE (`t14`.`$f2` IS NULL OR `t6`.`c` = 0 OR `t6`.`c` IS NULL)
AND (`t`.`p_type` IS NOT NULL OR `t6`.`c` = 0 OR `t6`.`c` IS NULL OR `t14`.`$f2` IS NOT NULL)
AND (`t6`.`ck` < `t6`.`c` IS NOT TRUE OR `t6`.`c` = 0 OR `t6`.`c` IS NULL OR `t14`.`$f2` IS NOT NULL
OR `t`.`p_type` IS NULL)
PREHOOK: type: QUERY
PREHOOK: Input: default@part
#### A masked pattern was here ####
POSTHOOK: query: explain extended
SELECT `t`.`p_name`
FROM (SELECT `p_name`, `p_type`, `p_size` + 1 AS `size`
FROM `part`) AS `t`
LEFT JOIN (SELECT `t5`.`size`, `t2`.`c`, `t2`.`ck`
FROM (SELECT `p_size` + 1 AS `+`, COUNT(*) AS `c`, COUNT(`p_type`) AS `ck`
FROM `part`
WHERE `p_size` IS NOT NULL
GROUP BY `p_size` + 1) AS `t2`
INNER JOIN (SELECT `p_size` + 1 AS `size`
FROM `part`
WHERE `p_size` IS NOT NULL
GROUP BY `p_size` + 1) AS `t5` ON `t2`.`+` = `t5`.`size`) AS `t6` ON `t`.`size` = `t6`.`size`
LEFT JOIN (SELECT `t9`.`p_type`, `t12`.`size`, TRUE AS `$f2`
FROM (SELECT `p_type`, `p_size` + 1 AS `+`
FROM `part`
WHERE `p_size` IS NOT NULL AND `p_type` IS NOT NULL
GROUP BY `p_type`, `p_size` + 1) AS `t9`
INNER JOIN (SELECT `p_size` + 1 AS `size`
FROM `part`
WHERE `p_size` IS NOT NULL
GROUP BY `p_size` + 1) AS `t12` ON `t9`.`+` = `t12`.`size`) AS `t14` ON `t`.`p_type` = `t14`.`p_type` AND `t`.`size` = `t14`.`size`
WHERE (`t14`.`$f2` IS NULL OR `t6`.`c` = 0 OR `t6`.`c` IS NULL)
AND (`t`.`p_type` IS NOT NULL OR `t6`.`c` = 0 OR `t6`.`c` IS NULL OR `t14`.`$f2` IS NOT NULL)
AND (`t6`.`ck` < `t6`.`c` IS NOT TRUE OR `t6`.`c` = 0 OR `t6`.`c` IS NULL OR `t14`.`$f2` IS NOT NULL
OR `t`.`p_type` IS NULL)
POSTHOOK: type: QUERY
POSTHOOK: Input: default@part
#### A masked pattern was here ####
OPTIMIZED SQL: SELECT `p_name`
FROM (SELECT `t`.`p_name`, `t`.`p_type`, `t`.`size`, `t5`.`$f0` AS `size0`, `t2`.`$f1` AS `c`, `t2`.`$f2` AS `ck`, `t12`.`p_type` AS `p_type0`, `t12`.`size` AS `size1`, `t12`.`$f2`
FROM (SELECT `p_name`, `p_type`, `p_size` + 1 AS `size`
FROM `default`.`part`) AS `t`
LEFT JOIN ((SELECT `p_size` + 1 AS `$f0`, COUNT(*) AS `$f1`, COUNT(`p_type`) AS `$f2`
FROM `default`.`part`
WHERE `p_size` IS NOT NULL
GROUP BY `p_size` + 1) AS `t2`
INNER JOIN (SELECT `p_size` + 1 AS `$f0`
FROM `default`.`part`
WHERE `p_size` IS NOT NULL
GROUP BY `p_size` + 1) AS `t5` ON `t2`.`$f0` = `t5`.`$f0`) ON `t`.`size` = `t5`.`$f0`
LEFT JOIN (SELECT `t8`.`$f0` AS `p_type`, `t11`.`$f0` AS `size`, TRUE AS `$f2`
FROM (SELECT `p_type` AS `$f0`, `p_size` + 1 AS `$f1`
FROM `default`.`part`
WHERE `p_size` IS NOT NULL AND `p_type` IS NOT NULL
GROUP BY `p_type`, `p_size` + 1) AS `t8`
INNER JOIN (SELECT `p_size` + 1 AS `$f0`
FROM `default`.`part`
WHERE `p_size` IS NOT NULL
GROUP BY `p_size` + 1) AS `t11` ON `t8`.`$f1` = `t11`.`$f0`) AS `t12` ON `t`.`p_type` = `t12`.`p_type` AND `t`.`size` = `t12`.`size`) AS `t13`
WHERE (`t13`.`$f2` IS NULL OR `t13`.`c` = 0 OR `t13`.`c` IS NULL) AND (`t13`.`ck` < (`t13`.`c` IS NOT TRUE) OR `t13`.`c` = 0 OR `t13`.`c` IS NULL OR `t13`.`$f2` IS NOT NULL OR `t13`.`p_type` IS NULL) AND (`t13`.`p_type` IS NOT NULL OR `t13`.`c` = 0 OR `t13`.`c` IS NULL OR `t13`.`$f2` IS NOT NULL)
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
STAGE PLANS:
Stage: Stage-1
Tez
#### A masked pattern was here ####
Edges:
Reducer 3 <- Map 1 (SIMPLE_EDGE)
Reducer 4 <- Reducer 3 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE)
Reducer 5 <- Reducer 4 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE)
Reducer 7 <- Map 6 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE)
Reducer 8 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE)
Reducer 9 <- Map 6 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
alias: part
filterExpr: p_size is not null (type: boolean)
Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: p_size is not null (type: boolean)
Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: (p_size + 1) (type: int)
outputColumnNames: _col0
Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int)
minReductionHashAggr: 0.5
mode: hash
outputColumnNames: _col0
Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
bucketingVersion: 2
key expressions: _col0 (type: int)
null sort order: z
numBuckets: -1
sort order: +
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE
tag: -1
auto parallelism: true
Reduce Output Operator
bucketingVersion: 2
key expressions: _col0 (type: int)
null sort order: z
numBuckets: -1
sort order: +
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE
tag: -1
auto parallelism: true
Execution mode: vectorized, llap
LLAP IO: all inputs
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
#### A masked pattern was here ####
Partition
base file name: part
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 p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment
columns.types int:string:string:string:string:int:string:double:string
#### A masked pattern was here ####
name default.part
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
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:
bucketing_version 2
column.name.delimiter ,
columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment
columns.comments
columns.types int:string:string:string:string:int:string:double:string
#### A masked pattern was here ####
name default.part
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.part
name: default.part
Truncated Path -> Alias:
/part [part]
Map 6
Map Operator Tree:
TableScan
alias: part
Statistics: Num rows: 26 Data size: 5954 Basic stats: COMPLETE Column stats: COMPLETE
GatherStats: false
Select Operator
expressions: p_name (type: string), p_type (type: string), (p_size + 1) (type: int)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 26 Data size: 5954 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
bucketingVersion: 2
key expressions: _col2 (type: int)
null sort order: z
numBuckets: -1
sort order: +
Map-reduce partition columns: _col2 (type: int)
Statistics: Num rows: 26 Data size: 5954 Basic stats: COMPLETE Column stats: COMPLETE
tag: 1
value expressions: _col0 (type: string), _col1 (type: string)
auto parallelism: true
Filter Operator
isSamplingPred: false
predicate: p_size is not null (type: boolean)
Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: (p_size + 1) (type: int), p_type (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(), count(_col1)
keys: _col0 (type: int)
minReductionHashAggr: 0.5
mode: hash
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 13 Data size: 260 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
bucketingVersion: 2
key expressions: _col0 (type: int)
null sort order: z
numBuckets: -1
sort order: +
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 13 Data size: 260 Basic stats: COMPLETE Column stats: COMPLETE
tag: -1
value expressions: _col1 (type: bigint), _col2 (type: bigint)
auto parallelism: true
Filter Operator
isSamplingPred: false
predicate: (p_size is not null and p_type is not null) (type: boolean)
Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: p_type (type: string), (p_size + 1) (type: int)
outputColumnNames: _col0, _col1
Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col1 (type: int), _col0 (type: string)
minReductionHashAggr: 0.0
mode: hash
outputColumnNames: _col0, _col1
Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
bucketingVersion: 2
key expressions: _col0 (type: int), _col1 (type: string)
null sort order: zz
numBuckets: -1
sort order: ++
Map-reduce partition columns: _col0 (type: int), _col1 (type: string)
Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
tag: -1
auto parallelism: true
Execution mode: vectorized, llap
LLAP IO: all inputs
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
#### A masked pattern was here ####
Partition
base file name: part
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 p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment
columns.types int:string:string:string:string:int:string:double:string
#### A masked pattern was here ####
name default.part
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
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:
bucketing_version 2
column.name.delimiter ,
columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment
columns.comments
columns.types int:string:string:string:string:int:string:double:string
#### A masked pattern was here ####
name default.part
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.part
name: default.part
Truncated Path -> Alias:
/part [part]
Reducer 3
Execution mode: vectorized, llap
Needs Tagging: false
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0
Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
bucketingVersion: 2
key expressions: _col0 (type: int)
null sort order: z
numBuckets: -1
sort order: +
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE
tag: 1
auto parallelism: true
Reducer 4
Execution mode: llap
Needs Tagging: false
Reduce Operator Tree:
Merge Join Operator
condition map:
Inner Join 0 to 1
keys:
0 _col1 (type: int)
1 _col0 (type: int)
outputColumnNames: _col0, _col2
Position of Big Table: 0
Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), _col2 (type: int), true (type: boolean)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
bucketingVersion: 2
key expressions: _col0 (type: string), _col1 (type: int)
null sort order: zz
numBuckets: -1
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: int)
Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
tag: 1
value expressions: _col2 (type: boolean)
auto parallelism: true
Reducer 5
Execution mode: llap
Needs Tagging: false
Reduce Operator Tree:
Merge Join Operator
condition map:
Left Outer Join 0 to 1
keys:
0 _col5 (type: string), _col6 (type: int)
1 _col0 (type: string), _col1 (type: int)
outputColumnNames: _col1, _col2, _col4, _col5, _col9
Position of Big Table: 0
Statistics: Num rows: 55 Data size: 12947 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col4 (type: string), _col5 (type: string), _col1 (type: bigint), _col2 (type: bigint), _col9 (type: boolean)
outputColumnNames: _col0, _col1, _col4, _col5, _col8
Statistics: Num rows: 55 Data size: 12947 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
isSamplingPred: false
predicate: ((_col8 is null or (_col4 = 0L) or _col4 is null) and ((_col5 < _col4 is not true) or (_col4 = 0L) or _col4 is null or _col8 is not null or _col1 is null) and (_col1 is not null or (_col4 = 0L) or _col4 is null or _col8 is not null)) (type: boolean)
Statistics: Num rows: 55 Data size: 12947 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
Statistics: Num rows: 55 Data size: 6655 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
bucketingVersion: 2
compressed: false
GlobalTableId: 0
#### A masked pattern was here ####
NumFilesPerFileSink: 1
Statistics: Num rows: 55 Data size: 6655 Basic stats: COMPLETE Column stats: COMPLETE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
properties:
bucketing_version -1
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
Reducer 7
Execution mode: llap
Needs Tagging: false
Reduce Operator Tree:
Merge Join Operator
condition map:
Right Outer Join 0 to 1
keys:
0 _col3 (type: int)
1 _col2 (type: int)
outputColumnNames: _col1, _col2, _col4, _col5, _col6
Position of Big Table: 0
Statistics: Num rows: 42 Data size: 9890 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
bucketingVersion: 2
key expressions: _col5 (type: string), _col6 (type: int)
null sort order: zz
numBuckets: -1
sort order: ++
Map-reduce partition columns: _col5 (type: string), _col6 (type: int)
Statistics: Num rows: 42 Data size: 9890 Basic stats: COMPLETE Column stats: COMPLETE
tag: 0
value expressions: _col1 (type: bigint), _col2 (type: bigint), _col4 (type: string)
auto parallelism: true
Reducer 8
Needs Tagging: false
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0
Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE
Dummy Store
Execution mode: llap
Needs Tagging: false
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0), count(VALUE._col1)
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 13 Data size: 260 Basic stats: COMPLETE Column stats: COMPLETE
Merge Join Operator
condition map:
Inner Join 0 to 1
keys:
0 _col0 (type: int)
1 _col0 (type: int)
outputColumnNames: _col1, _col2, _col3
Position of Big Table: 0
Statistics: Num rows: 13 Data size: 260 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
bucketingVersion: 2
key expressions: _col3 (type: int)
null sort order: z
numBuckets: -1
sort order: +
Map-reduce partition columns: _col3 (type: int)
Statistics: Num rows: 13 Data size: 260 Basic stats: COMPLETE Column stats: COMPLETE
tag: 0
value expressions: _col1 (type: bigint), _col2 (type: bigint)
auto parallelism: true
Reducer 9
Execution mode: vectorized, llap
Needs Tagging: false
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: int), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: string), _col0 (type: int)
outputColumnNames: _col0, _col1
Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
bucketingVersion: 2
key expressions: _col1 (type: int)
null sort order: z
numBuckets: -1
sort order: +
Map-reduce partition columns: _col1 (type: int)
Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
tag: 0
value expressions: _col0 (type: string)
auto parallelism: true
Stage: Stage-0
Fetch Operator
limit: -1
Processor Tree:
ListSink