blob: 73ad8aee3bed922fb42caad49752e2111ff2d855 [file] [log] [blame]
PREHOOK: query: create table testsrc ( `key` int,`val` string)
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@testsrc
POSTHOOK: query: create table testsrc ( `key` int,`val` string)
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@testsrc
PREHOOK: query: load data local inpath '../../data/files/kv1.txt' overwrite into table testsrc
PREHOOK: type: LOAD
#### A masked pattern was here ####
PREHOOK: Output: default@testsrc
POSTHOOK: query: load data local inpath '../../data/files/kv1.txt' overwrite into table testsrc
POSTHOOK: type: LOAD
#### A masked pattern was here ####
POSTHOOK: Output: default@testsrc
PREHOOK: query: drop table if exists orderpayment_small
PREHOOK: type: DROPTABLE
POSTHOOK: query: drop table if exists orderpayment_small
POSTHOOK: type: DROPTABLE
PREHOOK: query: create table orderpayment_small (`dealid` int,`date` string,`time` string, `cityid` int, `userid` int)
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@orderpayment_small
POSTHOOK: query: create table orderpayment_small (`dealid` int,`date` string,`time` string, `cityid` int, `userid` int)
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@orderpayment_small
PREHOOK: query: insert overwrite table orderpayment_small select 748, '2011-03-24', '2011-03-24', 55 ,5372613 from testsrc tablesample (1 rows)
PREHOOK: type: QUERY
PREHOOK: Input: default@testsrc
PREHOOK: Output: default@orderpayment_small
POSTHOOK: query: insert overwrite table orderpayment_small select 748, '2011-03-24', '2011-03-24', 55 ,5372613 from testsrc tablesample (1 rows)
POSTHOOK: type: QUERY
POSTHOOK: Input: default@testsrc
POSTHOOK: Output: default@orderpayment_small
POSTHOOK: Lineage: orderpayment_small.cityid SIMPLE []
POSTHOOK: Lineage: orderpayment_small.date SIMPLE []
POSTHOOK: Lineage: orderpayment_small.dealid SIMPLE []
POSTHOOK: Lineage: orderpayment_small.time SIMPLE []
POSTHOOK: Lineage: orderpayment_small.userid SIMPLE []
PREHOOK: query: drop table if exists user_small
PREHOOK: type: DROPTABLE
POSTHOOK: query: drop table if exists user_small
POSTHOOK: type: DROPTABLE
PREHOOK: query: create table user_small( userid int)
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@user_small
POSTHOOK: query: create table user_small( userid int)
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@user_small
PREHOOK: query: insert overwrite table user_small select key from testsrc tablesample (100 rows)
PREHOOK: type: QUERY
PREHOOK: Input: default@testsrc
PREHOOK: Output: default@user_small
POSTHOOK: query: insert overwrite table user_small select key from testsrc tablesample (100 rows)
POSTHOOK: type: QUERY
POSTHOOK: Input: default@testsrc
POSTHOOK: Output: default@user_small
POSTHOOK: Lineage: user_small.userid SIMPLE [(testsrc)testsrc.FieldSchema(name:key, type:int, comment:null), ]
PREHOOK: query: explain extended SELECT
`dim_pay_date`.`date`
, `deal`.`dealid`
FROM `orderpayment_small` `orderpayment`
JOIN `orderpayment_small` `dim_pay_date` ON `dim_pay_date`.`date` = `orderpayment`.`date`
JOIN `orderpayment_small` `deal` ON `deal`.`dealid` = `orderpayment`.`dealid`
JOIN `orderpayment_small` `order_city` ON `order_city`.`cityid` = `orderpayment`.`cityid`
JOIN `user_small` `user` ON `user`.`userid` = `orderpayment`.`userid`
limit 5
PREHOOK: type: QUERY
PREHOOK: Input: default@orderpayment_small
PREHOOK: Input: default@user_small
#### A masked pattern was here ####
POSTHOOK: query: explain extended SELECT
`dim_pay_date`.`date`
, `deal`.`dealid`
FROM `orderpayment_small` `orderpayment`
JOIN `orderpayment_small` `dim_pay_date` ON `dim_pay_date`.`date` = `orderpayment`.`date`
JOIN `orderpayment_small` `deal` ON `deal`.`dealid` = `orderpayment`.`dealid`
JOIN `orderpayment_small` `order_city` ON `order_city`.`cityid` = `orderpayment`.`cityid`
JOIN `user_small` `user` ON `user`.`userid` = `orderpayment`.`userid`
limit 5
POSTHOOK: type: QUERY
POSTHOOK: Input: default@orderpayment_small
POSTHOOK: Input: default@user_small
#### A masked pattern was here ####
OPTIMIZED SQL: SELECT `t4`.`date`, `t6`.`dealid`
FROM (SELECT `userid`
FROM `default`.`user_small`
WHERE `userid` IS NOT NULL) AS `t0`
INNER JOIN ((SELECT `dealid`, `date`, `cityid`, `userid`
FROM `default`.`orderpayment_small`
WHERE `date` IS NOT NULL AND `dealid` IS NOT NULL AND (`cityid` IS NOT NULL AND `userid` IS NOT NULL)) AS `t2` INNER JOIN (SELECT `date`
FROM `default`.`orderpayment_small`
WHERE `date` IS NOT NULL) AS `t4` ON `t2`.`date` = `t4`.`date` INNER JOIN (SELECT `dealid`
FROM `default`.`orderpayment_small`
WHERE `dealid` IS NOT NULL) AS `t6` ON `t2`.`dealid` = `t6`.`dealid` INNER JOIN (SELECT `cityid`
FROM `default`.`orderpayment_small`
WHERE `cityid` IS NOT NULL) AS `t8` ON `t2`.`cityid` = `t8`.`cityid`) ON `t0`.`userid` = `t2`.`userid`
LIMIT 5
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 1 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
Reducer 4 <- Map 1 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE)
Reducer 5 <- Map 7 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
alias: orderpayment
filterExpr: ((date is not null and dealid is not null and cityid is not null and userid is not null) or dealid is not null or cityid is not null) (type: boolean)
Statistics: Num rows: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: (date is not null and dealid is not null and cityid is not null and userid is not null) (type: boolean)
Statistics: Num rows: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: dealid (type: int), date (type: string), cityid (type: int), userid (type: int)
outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
bucketingVersion: 2
key expressions: _col1 (type: string)
null sort order: z
numBuckets: -1
sort order: +
Map-reduce partition columns: _col1 (type: string)
Statistics: Num rows: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE
tag: 0
value expressions: _col0 (type: int), _col2 (type: int), _col3 (type: int)
auto parallelism: true
Filter Operator
isSamplingPred: false
predicate: dealid is not null (type: boolean)
Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: dealid (type: int)
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 4 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: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
tag: 1
auto parallelism: true
Filter Operator
isSamplingPred: false
predicate: cityid is not null (type: boolean)
Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: cityid (type: int)
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 4 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: 1 Data size: 4 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: orderpayment_small
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 dealid,date,time,cityid,userid
columns.types int:string:string:int:int
#### A masked pattern was here ####
name default.orderpayment_small
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 dealid,date,time,cityid,userid
columns.comments
columns.types int:string:string:int:int
#### A masked pattern was here ####
name default.orderpayment_small
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.orderpayment_small
name: default.orderpayment_small
Truncated Path -> Alias:
/orderpayment_small [orderpayment]
Map 6
Map Operator Tree:
TableScan
alias: dim_pay_date
filterExpr: date is not null (type: boolean)
Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: date is not null (type: boolean)
Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: date (type: string)
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
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: 94 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: orderpayment_small
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 dealid,date,time,cityid,userid
columns.types int:string:string:int:int
#### A masked pattern was here ####
name default.orderpayment_small
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 dealid,date,time,cityid,userid
columns.comments
columns.types int:string:string:int:int
#### A masked pattern was here ####
name default.orderpayment_small
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.orderpayment_small
name: default.orderpayment_small
Truncated Path -> Alias:
/orderpayment_small [dim_pay_date]
Map 7
Map Operator Tree:
TableScan
alias: user
filterExpr: userid is not null (type: boolean)
Statistics: Num rows: 100 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: userid is not null (type: boolean)
Statistics: Num rows: 100 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: userid (type: int)
outputColumnNames: _col0
Statistics: Num rows: 100 Data size: 400 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: 100 Data size: 400 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: user_small
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 userid
columns.types int
#### A masked pattern was here ####
name default.user_small
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 userid
columns.comments
columns.types int
#### A masked pattern was here ####
name default.user_small
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.user_small
name: default.user_small
Truncated Path -> Alias:
/user_small [user]
Reducer 2
Execution mode: llap
Needs Tagging: false
Reduce Operator Tree:
Merge Join Operator
condition map:
Inner Join 0 to 1
keys:
0 _col1 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col2, _col3, _col4
Position of Big Table: 0
Statistics: Num rows: 1 Data size: 106 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: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE
tag: 0
value expressions: _col2 (type: int), _col3 (type: int), _col4 (type: string)
auto parallelism: true
Reducer 3
Execution mode: llap
Needs Tagging: false
Reduce Operator Tree:
Merge Join Operator
condition map:
Inner Join 0 to 1
keys:
0 _col0 (type: int)
1 _col0 (type: int)
outputColumnNames: _col2, _col3, _col4, _col5
Position of Big Table: 0
Statistics: Num rows: 1 Data size: 106 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: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE
tag: 0
value expressions: _col3 (type: int), _col4 (type: string), _col5 (type: int)
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 _col2 (type: int)
1 _col0 (type: int)
outputColumnNames: _col3, _col4, _col5
Position of Big Table: 0
Statistics: Num rows: 1 Data size: 102 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: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE
tag: 0
value expressions: _col4 (type: string), _col5 (type: int)
auto parallelism: true
Reducer 5
Execution mode: llap
Needs Tagging: false
Reduce Operator Tree:
Merge Join Operator
condition map:
Inner Join 0 to 1
keys:
0 _col3 (type: int)
1 _col0 (type: int)
outputColumnNames: _col4, _col5
Position of Big Table: 1
Statistics: Num rows: 1 Data size: 98 Basic stats: COMPLETE Column stats: COMPLETE
Limit
Number of rows: 5
Statistics: Num rows: 1 Data size: 98 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col4 (type: string), _col5 (type: int)
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 98 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: 1 Data size: 98 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,_col1
columns.types 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: 5
Processor Tree:
ListSink
PREHOOK: query: SELECT
`dim_pay_date`.`date`
, `deal`.`dealid`
FROM `orderpayment_small` `orderpayment`
JOIN `orderpayment_small` `dim_pay_date` ON `dim_pay_date`.`date` = `orderpayment`.`date`
JOIN `orderpayment_small` `deal` ON `deal`.`dealid` = `orderpayment`.`dealid`
JOIN `orderpayment_small` `order_city` ON `order_city`.`cityid` = `orderpayment`.`cityid`
JOIN `user_small` `user` ON `user`.`userid` = `orderpayment`.`userid`
limit 5
PREHOOK: type: QUERY
PREHOOK: Input: default@orderpayment_small
PREHOOK: Input: default@user_small
#### A masked pattern was here ####
POSTHOOK: query: SELECT
`dim_pay_date`.`date`
, `deal`.`dealid`
FROM `orderpayment_small` `orderpayment`
JOIN `orderpayment_small` `dim_pay_date` ON `dim_pay_date`.`date` = `orderpayment`.`date`
JOIN `orderpayment_small` `deal` ON `deal`.`dealid` = `orderpayment`.`dealid`
JOIN `orderpayment_small` `order_city` ON `order_city`.`cityid` = `orderpayment`.`cityid`
JOIN `user_small` `user` ON `user`.`userid` = `orderpayment`.`userid`
limit 5
POSTHOOK: type: QUERY
POSTHOOK: Input: default@orderpayment_small
POSTHOOK: Input: default@user_small
#### A masked pattern was here ####