blob: 40dd18188b43799c316d439445d1a5994e576194 [file] [log] [blame]
PREHOOK: query: drop table if exists char_part_tbl1
PREHOOK: type: DROPTABLE
POSTHOOK: query: drop table if exists char_part_tbl1
POSTHOOK: type: DROPTABLE
PREHOOK: query: drop table if exists char_part_tbl2
PREHOOK: type: DROPTABLE
POSTHOOK: query: drop table if exists char_part_tbl2
POSTHOOK: type: DROPTABLE
PREHOOK: query: create table studenttab(name string, age int, gpa double) clustered by (age) into 2 buckets stored as orc tblproperties('transactional'='true')
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@studenttab
POSTHOOK: query: create table studenttab(name string, age int, gpa double) clustered by (age) into 2 buckets stored as orc tblproperties('transactional'='true')
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@studenttab
PREHOOK: query: insert into table studenttab values ('calvin garcia',56,2.50), ('oscar miller',66,3.00), ('(yuri xylophone',30,2.74),('alice underhill',46,3.50)
PREHOOK: type: QUERY
PREHOOK: Input: _dummy_database@_dummy_table
PREHOOK: Output: default@studenttab
POSTHOOK: query: insert into table studenttab values ('calvin garcia',56,2.50), ('oscar miller',66,3.00), ('(yuri xylophone',30,2.74),('alice underhill',46,3.50)
POSTHOOK: type: QUERY
POSTHOOK: Input: _dummy_database@_dummy_table
POSTHOOK: Output: default@studenttab
POSTHOOK: Lineage: studenttab.age SCRIPT []
POSTHOOK: Lineage: studenttab.gpa SCRIPT []
POSTHOOK: Lineage: studenttab.name SCRIPT []
PREHOOK: query: create table char_tbl1(name string, age int) partitioned by(gpa char(50)) stored as orc
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@char_tbl1
POSTHOOK: query: create table char_tbl1(name string, age int) partitioned by(gpa char(50)) stored as orc
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@char_tbl1
PREHOOK: query: create table char_tbl2(name string, age int) partitioned by(gpa char(5)) stored as orc
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@char_tbl2
POSTHOOK: query: create table char_tbl2(name string, age int) partitioned by(gpa char(5)) stored as orc
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@char_tbl2
PREHOOK: query: insert into table char_tbl1 partition(gpa='3.5') select name, age from studenttab where gpa = 3.5
PREHOOK: type: QUERY
PREHOOK: Input: default@studenttab
PREHOOK: Output: default@char_tbl1@gpa=3.5
POSTHOOK: query: insert into table char_tbl1 partition(gpa='3.5') select name, age from studenttab where gpa = 3.5
POSTHOOK: type: QUERY
POSTHOOK: Input: default@studenttab
POSTHOOK: Output: default@char_tbl1@gpa=3.5
POSTHOOK: Lineage: char_tbl1 PARTITION(gpa=3.5 ).age SIMPLE [(studenttab)studenttab.FieldSchema(name:age, type:int, comment:null), ]
POSTHOOK: Lineage: char_tbl1 PARTITION(gpa=3.5 ).name SIMPLE [(studenttab)studenttab.FieldSchema(name:name, type:string, comment:null), ]
PREHOOK: query: insert into table char_tbl1 partition(gpa='2.5') select name, age from studenttab where gpa = 2.5
PREHOOK: type: QUERY
PREHOOK: Input: default@studenttab
PREHOOK: Output: default@char_tbl1@gpa=2.5
POSTHOOK: query: insert into table char_tbl1 partition(gpa='2.5') select name, age from studenttab where gpa = 2.5
POSTHOOK: type: QUERY
POSTHOOK: Input: default@studenttab
POSTHOOK: Output: default@char_tbl1@gpa=2.5
POSTHOOK: Lineage: char_tbl1 PARTITION(gpa=2.5 ).age SIMPLE [(studenttab)studenttab.FieldSchema(name:age, type:int, comment:null), ]
POSTHOOK: Lineage: char_tbl1 PARTITION(gpa=2.5 ).name SIMPLE [(studenttab)studenttab.FieldSchema(name:name, type:string, comment:null), ]
PREHOOK: query: insert into table char_tbl2 partition(gpa='3.5') select name, age from studenttab where gpa = 3.5
PREHOOK: type: QUERY
PREHOOK: Input: default@studenttab
PREHOOK: Output: default@char_tbl2@gpa=3.5
POSTHOOK: query: insert into table char_tbl2 partition(gpa='3.5') select name, age from studenttab where gpa = 3.5
POSTHOOK: type: QUERY
POSTHOOK: Input: default@studenttab
POSTHOOK: Output: default@char_tbl2@gpa=3.5
POSTHOOK: Lineage: char_tbl2 PARTITION(gpa=3.5 ).age SIMPLE [(studenttab)studenttab.FieldSchema(name:age, type:int, comment:null), ]
POSTHOOK: Lineage: char_tbl2 PARTITION(gpa=3.5 ).name SIMPLE [(studenttab)studenttab.FieldSchema(name:name, type:string, comment:null), ]
PREHOOK: query: insert into table char_tbl2 partition(gpa='3') select name, age from studenttab where gpa = 3
PREHOOK: type: QUERY
PREHOOK: Input: default@studenttab
PREHOOK: Output: default@char_tbl2@gpa=3
POSTHOOK: query: insert into table char_tbl2 partition(gpa='3') select name, age from studenttab where gpa = 3
POSTHOOK: type: QUERY
POSTHOOK: Input: default@studenttab
POSTHOOK: Output: default@char_tbl2@gpa=3
POSTHOOK: Lineage: char_tbl2 PARTITION(gpa=3 ).age SIMPLE [(studenttab)studenttab.FieldSchema(name:age, type:int, comment:null), ]
POSTHOOK: Lineage: char_tbl2 PARTITION(gpa=3 ).name SIMPLE [(studenttab)studenttab.FieldSchema(name:name, type:string, comment:null), ]
PREHOOK: query: show partitions char_tbl1
PREHOOK: type: SHOWPARTITIONS
PREHOOK: Input: default@char_tbl1
POSTHOOK: query: show partitions char_tbl1
POSTHOOK: type: SHOWPARTITIONS
POSTHOOK: Input: default@char_tbl1
gpa=2.5
gpa=3.5
PREHOOK: query: show partitions char_tbl2
PREHOOK: type: SHOWPARTITIONS
PREHOOK: Input: default@char_tbl2
POSTHOOK: query: show partitions char_tbl2
POSTHOOK: type: SHOWPARTITIONS
POSTHOOK: Input: default@char_tbl2
gpa=3
gpa=3.5
PREHOOK: query: explain vectorization select c1.name, c1.age, c1.gpa, c2.name, c2.age, c2.gpa from char_tbl1 c1 join char_tbl2 c2 on (c1.gpa = c2.gpa)
PREHOOK: type: QUERY
POSTHOOK: query: explain vectorization select c1.name, c1.age, c1.gpa, c2.name, c2.age, c2.gpa from char_tbl1 c1 join char_tbl2 c2 on (c1.gpa = c2.gpa)
POSTHOOK: type: QUERY
PLAN VECTORIZATION:
enabled: true
enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
STAGE PLANS:
Stage: Stage-1
Map Reduce
Map Operator Tree:
TableScan
alias: c1
Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: name (type: string), age (type: int), gpa (type: char(50))
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col2 (type: char(50))
sort order: +
Map-reduce partition columns: _col2 (type: char(50))
Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: string), _col1 (type: int)
TableScan
alias: c2
Statistics: Num rows: 2 Data size: 203 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: name (type: string), age (type: int), gpa (type: char(5))
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 2 Data size: 203 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col2 (type: char(50))
sort order: +
Map-reduce partition columns: _col2 (type: char(50))
Statistics: Num rows: 2 Data size: 203 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: string), _col1 (type: int)
Map Vectorization:
enabled: false
enabledConditionsNotMet: Vectorized map work only works with 1 TableScanOperator IS false
Reduce Vectorization:
enabled: false
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true
enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false
Reduce Operator Tree:
Join Operator
condition map:
Inner Join 0 to 1
keys:
0 _col2 (type: char(50))
1 _col2 (type: char(50))
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
Fetch Operator
limit: -1
Processor Tree:
ListSink
PREHOOK: query: select c1.name, c1.age, c1.gpa, c2.name, c2.age, c2.gpa from char_tbl1 c1 join char_tbl2 c2 on (c1.gpa = c2.gpa)
PREHOOK: type: QUERY
PREHOOK: Input: default@char_tbl1
PREHOOK: Input: default@char_tbl1@gpa=2.5
PREHOOK: Input: default@char_tbl1@gpa=3.5
PREHOOK: Input: default@char_tbl2
PREHOOK: Input: default@char_tbl2@gpa=3
PREHOOK: Input: default@char_tbl2@gpa=3.5
#### A masked pattern was here ####
POSTHOOK: query: select c1.name, c1.age, c1.gpa, c2.name, c2.age, c2.gpa from char_tbl1 c1 join char_tbl2 c2 on (c1.gpa = c2.gpa)
POSTHOOK: type: QUERY
POSTHOOK: Input: default@char_tbl1
POSTHOOK: Input: default@char_tbl1@gpa=2.5
POSTHOOK: Input: default@char_tbl1@gpa=3.5
POSTHOOK: Input: default@char_tbl2
POSTHOOK: Input: default@char_tbl2@gpa=3
POSTHOOK: Input: default@char_tbl2@gpa=3.5
#### A masked pattern was here ####
alice underhill 46 3.5 alice underhill 46 3.5
PREHOOK: query: select c1.name, c1.age, c1.gpa, c2.name, c2.age, c2.gpa from char_tbl1 c1 join char_tbl2 c2 on (c1.gpa = c2.gpa)
PREHOOK: type: QUERY
PREHOOK: Input: default@char_tbl1
PREHOOK: Input: default@char_tbl1@gpa=2.5
PREHOOK: Input: default@char_tbl1@gpa=3.5
PREHOOK: Input: default@char_tbl2
PREHOOK: Input: default@char_tbl2@gpa=3
PREHOOK: Input: default@char_tbl2@gpa=3.5
#### A masked pattern was here ####
POSTHOOK: query: select c1.name, c1.age, c1.gpa, c2.name, c2.age, c2.gpa from char_tbl1 c1 join char_tbl2 c2 on (c1.gpa = c2.gpa)
POSTHOOK: type: QUERY
POSTHOOK: Input: default@char_tbl1
POSTHOOK: Input: default@char_tbl1@gpa=2.5
POSTHOOK: Input: default@char_tbl1@gpa=3.5
POSTHOOK: Input: default@char_tbl2
POSTHOOK: Input: default@char_tbl2@gpa=3
POSTHOOK: Input: default@char_tbl2@gpa=3.5
#### A masked pattern was here ####
alice underhill 46 3.5 alice underhill 46 3.5