You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by jc...@apache.org on 2018/04/10 09:29:49 UTC
[11/24] hive git commit: HIVE-18839: Implement incremental rebuild
for materialized views (only insert operations in source tables) (Jesus
Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/be420098/ql/src/test/results/clientpositive/materialized_view_rewrite_4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/materialized_view_rewrite_4.q.out b/ql/src/test/results/clientpositive/materialized_view_rewrite_4.q.out
deleted file mode 100644
index 7301571..0000000
--- a/ql/src/test/results/clientpositive/materialized_view_rewrite_4.q.out
+++ /dev/null
@@ -1,944 +0,0 @@
-PREHOOK: query: create table emps (
- empid int,
- deptno int,
- name varchar(256),
- salary float,
- commission int)
-stored as orc TBLPROPERTIES ('transactional'='true')
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@emps
-POSTHOOK: query: create table emps (
- empid int,
- deptno int,
- name varchar(256),
- salary float,
- commission int)
-stored as orc TBLPROPERTIES ('transactional'='true')
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@emps
-PREHOOK: query: insert into emps values (100, 10, 'Bill', 10000, 1000), (200, 20, 'Eric', 8000, 500),
- (150, 10, 'Sebastian', 7000, null), (110, 10, 'Theodore', 10000, 250), (110, 10, 'Bill', 10000, 250)
-PREHOOK: type: QUERY
-PREHOOK: Input: _dummy_database@_dummy_table
-PREHOOK: Output: default@emps
-POSTHOOK: query: insert into emps values (100, 10, 'Bill', 10000, 1000), (200, 20, 'Eric', 8000, 500),
- (150, 10, 'Sebastian', 7000, null), (110, 10, 'Theodore', 10000, 250), (110, 10, 'Bill', 10000, 250)
-POSTHOOK: type: QUERY
-POSTHOOK: Input: _dummy_database@_dummy_table
-POSTHOOK: Output: default@emps
-POSTHOOK: Lineage: emps.commission SCRIPT []
-POSTHOOK: Lineage: emps.deptno SCRIPT []
-POSTHOOK: Lineage: emps.empid SCRIPT []
-POSTHOOK: Lineage: emps.name SCRIPT []
-POSTHOOK: Lineage: emps.salary SCRIPT []
-PREHOOK: query: analyze table emps compute statistics for columns
-PREHOOK: type: QUERY
-PREHOOK: Input: default@emps
-PREHOOK: Output: default@emps
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table emps compute statistics for columns
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@emps
-POSTHOOK: Output: default@emps
-#### A masked pattern was here ####
-PREHOOK: query: create table depts (
- deptno int,
- name varchar(256),
- locationid int)
-stored as orc TBLPROPERTIES ('transactional'='true')
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@depts
-POSTHOOK: query: create table depts (
- deptno int,
- name varchar(256),
- locationid int)
-stored as orc TBLPROPERTIES ('transactional'='true')
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@depts
-PREHOOK: query: insert into depts values (10, 'Sales', 10), (30, 'Marketing', null), (20, 'HR', 20)
-PREHOOK: type: QUERY
-PREHOOK: Input: _dummy_database@_dummy_table
-PREHOOK: Output: default@depts
-POSTHOOK: query: insert into depts values (10, 'Sales', 10), (30, 'Marketing', null), (20, 'HR', 20)
-POSTHOOK: type: QUERY
-POSTHOOK: Input: _dummy_database@_dummy_table
-POSTHOOK: Output: default@depts
-POSTHOOK: Lineage: depts.deptno SCRIPT []
-POSTHOOK: Lineage: depts.locationid SCRIPT []
-POSTHOOK: Lineage: depts.name SCRIPT []
-PREHOOK: query: analyze table depts compute statistics for columns
-PREHOOK: type: QUERY
-PREHOOK: Input: default@depts
-PREHOOK: Output: default@depts
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table depts compute statistics for columns
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@depts
-POSTHOOK: Output: default@depts
-#### A masked pattern was here ####
-PREHOOK: query: create table dependents (
- empid int,
- name varchar(256))
-stored as orc TBLPROPERTIES ('transactional'='true')
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@dependents
-POSTHOOK: query: create table dependents (
- empid int,
- name varchar(256))
-stored as orc TBLPROPERTIES ('transactional'='true')
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@dependents
-PREHOOK: query: insert into dependents values (10, 'Michael'), (10, 'Jane')
-PREHOOK: type: QUERY
-PREHOOK: Input: _dummy_database@_dummy_table
-PREHOOK: Output: default@dependents
-POSTHOOK: query: insert into dependents values (10, 'Michael'), (10, 'Jane')
-POSTHOOK: type: QUERY
-POSTHOOK: Input: _dummy_database@_dummy_table
-POSTHOOK: Output: default@dependents
-POSTHOOK: Lineage: dependents.empid SCRIPT []
-POSTHOOK: Lineage: dependents.name SCRIPT []
-PREHOOK: query: analyze table dependents compute statistics for columns
-PREHOOK: type: QUERY
-PREHOOK: Input: default@dependents
-PREHOOK: Output: default@dependents
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table dependents compute statistics for columns
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@dependents
-POSTHOOK: Output: default@dependents
-#### A masked pattern was here ####
-PREHOOK: query: create table locations (
- locationid int,
- name varchar(256))
-stored as orc TBLPROPERTIES ('transactional'='true')
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@locations
-POSTHOOK: query: create table locations (
- locationid int,
- name varchar(256))
-stored as orc TBLPROPERTIES ('transactional'='true')
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@locations
-PREHOOK: query: insert into locations values (10, 'San Francisco'), (10, 'San Diego')
-PREHOOK: type: QUERY
-PREHOOK: Input: _dummy_database@_dummy_table
-PREHOOK: Output: default@locations
-POSTHOOK: query: insert into locations values (10, 'San Francisco'), (10, 'San Diego')
-POSTHOOK: type: QUERY
-POSTHOOK: Input: _dummy_database@_dummy_table
-POSTHOOK: Output: default@locations
-POSTHOOK: Lineage: locations.locationid SCRIPT []
-POSTHOOK: Lineage: locations.name SCRIPT []
-PREHOOK: query: analyze table locations compute statistics for columns
-PREHOOK: type: QUERY
-PREHOOK: Input: default@locations
-PREHOOK: Output: default@locations
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table locations compute statistics for columns
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@locations
-POSTHOOK: Output: default@locations
-#### A masked pattern was here ####
-PREHOOK: query: alter table emps add constraint pk1 primary key (empid) disable novalidate rely
-PREHOOK: type: ALTERTABLE_ADDCONSTRAINT
-POSTHOOK: query: alter table emps add constraint pk1 primary key (empid) disable novalidate rely
-POSTHOOK: type: ALTERTABLE_ADDCONSTRAINT
-PREHOOK: query: alter table depts add constraint pk2 primary key (deptno) disable novalidate rely
-PREHOOK: type: ALTERTABLE_ADDCONSTRAINT
-POSTHOOK: query: alter table depts add constraint pk2 primary key (deptno) disable novalidate rely
-POSTHOOK: type: ALTERTABLE_ADDCONSTRAINT
-PREHOOK: query: alter table dependents add constraint pk3 primary key (empid) disable novalidate rely
-PREHOOK: type: ALTERTABLE_ADDCONSTRAINT
-POSTHOOK: query: alter table dependents add constraint pk3 primary key (empid) disable novalidate rely
-POSTHOOK: type: ALTERTABLE_ADDCONSTRAINT
-PREHOOK: query: alter table locations add constraint pk4 primary key (locationid) disable novalidate rely
-PREHOOK: type: ALTERTABLE_ADDCONSTRAINT
-POSTHOOK: query: alter table locations add constraint pk4 primary key (locationid) disable novalidate rely
-POSTHOOK: type: ALTERTABLE_ADDCONSTRAINT
-PREHOOK: query: alter table emps add constraint fk1 foreign key (deptno) references depts(deptno) disable novalidate rely
-PREHOOK: type: ALTERTABLE_ADDCONSTRAINT
-POSTHOOK: query: alter table emps add constraint fk1 foreign key (deptno) references depts(deptno) disable novalidate rely
-POSTHOOK: type: ALTERTABLE_ADDCONSTRAINT
-PREHOOK: query: alter table depts add constraint fk2 foreign key (locationid) references locations(locationid) disable novalidate rely
-PREHOOK: type: ALTERTABLE_ADDCONSTRAINT
-POSTHOOK: query: alter table depts add constraint fk2 foreign key (locationid) references locations(locationid) disable novalidate rely
-POSTHOOK: type: ALTERTABLE_ADDCONSTRAINT
-PREHOOK: query: create materialized view mv1 enable rewrite as
-select name, salary, count(*) as c, sum(empid) as s
-from emps group by name, salary
-PREHOOK: type: CREATE_MATERIALIZED_VIEW
-PREHOOK: Input: default@emps
-PREHOOK: Output: database:default
-PREHOOK: Output: default@mv1
-POSTHOOK: query: create materialized view mv1 enable rewrite as
-select name, salary, count(*) as c, sum(empid) as s
-from emps group by name, salary
-POSTHOOK: type: CREATE_MATERIALIZED_VIEW
-POSTHOOK: Input: default@emps
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@mv1
-PREHOOK: query: analyze table mv1 compute statistics for columns
-PREHOOK: type: QUERY
-PREHOOK: Input: default@mv1
-PREHOOK: Output: default@mv1
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1 compute statistics for columns
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@mv1
-POSTHOOK: Output: default@mv1
-#### A masked pattern was here ####
-PREHOOK: query: explain
-select name, count(*) as c, sum(empid) as s
-from emps group by name
-PREHOOK: type: QUERY
-POSTHOOK: query: explain
-select name, count(*) as c, sum(empid) as s
-from emps group by name
-POSTHOOK: type: QUERY
-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: default.mv1
- Statistics: Num rows: 4 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: name (type: varchar(256)), c (type: bigint), s (type: bigint)
- outputColumnNames: name, c, s
- Statistics: Num rows: 4 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: $sum0(c), sum(s)
- keys: name (type: varchar(256))
- mode: hash
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 2 Data size: 212 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: varchar(256))
- sort order: +
- Map-reduce partition columns: _col0 (type: varchar(256))
- Statistics: Num rows: 2 Data size: 212 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col1 (type: bigint), _col2 (type: bigint)
- Reduce Operator Tree:
- Group By Operator
- aggregations: $sum0(VALUE._col0), sum(VALUE._col1)
- keys: KEY._col0 (type: varchar(256))
- mode: mergepartial
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 2 Data size: 212 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 2 Data size: 212 Basic stats: COMPLETE Column stats: COMPLETE
- 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 name, count(*) as c, sum(empid) as s
-from emps group by name
-PREHOOK: type: QUERY
-PREHOOK: Input: default@emps
-PREHOOK: Input: default@mv1
-#### A masked pattern was here ####
-POSTHOOK: query: select name, count(*) as c, sum(empid) as s
-from emps group by name
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@emps
-POSTHOOK: Input: default@mv1
-#### A masked pattern was here ####
-Bill 2 210
-Eric 1 200
-Sebastian 1 150
-Theodore 1 110
-PREHOOK: query: drop materialized view mv1
-PREHOOK: type: DROP_MATERIALIZED_VIEW
-PREHOOK: Input: default@mv1
-PREHOOK: Output: default@mv1
-POSTHOOK: query: drop materialized view mv1
-POSTHOOK: type: DROP_MATERIALIZED_VIEW
-POSTHOOK: Input: default@mv1
-POSTHOOK: Output: default@mv1
-PREHOOK: query: create materialized view mv1 enable rewrite as
-select name, salary, count(*) as c, sum(empid) as s
-from emps group by name, salary
-PREHOOK: type: CREATE_MATERIALIZED_VIEW
-PREHOOK: Input: default@emps
-PREHOOK: Output: database:default
-PREHOOK: Output: default@mv1
-POSTHOOK: query: create materialized view mv1 enable rewrite as
-select name, salary, count(*) as c, sum(empid) as s
-from emps group by name, salary
-POSTHOOK: type: CREATE_MATERIALIZED_VIEW
-POSTHOOK: Input: default@emps
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@mv1
-PREHOOK: query: analyze table mv1 compute statistics for columns
-PREHOOK: type: QUERY
-PREHOOK: Input: default@mv1
-PREHOOK: Output: default@mv1
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1 compute statistics for columns
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@mv1
-POSTHOOK: Output: default@mv1
-#### A masked pattern was here ####
-PREHOOK: query: explain
-select salary, name, sum(empid) as s, count(*) as c
-from emps group by name, salary
-PREHOOK: type: QUERY
-POSTHOOK: query: explain
-select salary, name, sum(empid) as s, count(*) as c
-from emps group by name, salary
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-0 is a root stage
-
-STAGE PLANS:
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- TableScan
- alias: default.mv1
- Statistics: Num rows: 4 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: salary (type: float), name (type: varchar(256)), s (type: bigint), c (type: bigint)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 4 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE
- ListSink
-
-PREHOOK: query: select salary, name, sum(empid) as s, count(*) as c
-from emps group by name, salary
-PREHOOK: type: QUERY
-PREHOOK: Input: default@emps
-PREHOOK: Input: default@mv1
-#### A masked pattern was here ####
-POSTHOOK: query: select salary, name, sum(empid) as s, count(*) as c
-from emps group by name, salary
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@emps
-POSTHOOK: Input: default@mv1
-#### A masked pattern was here ####
-10000.0 Bill 210 2
-10000.0 Theodore 110 1
-7000.0 Sebastian 150 1
-8000.0 Eric 200 1
-PREHOOK: query: drop materialized view mv1
-PREHOOK: type: DROP_MATERIALIZED_VIEW
-PREHOOK: Input: default@mv1
-PREHOOK: Output: default@mv1
-POSTHOOK: query: drop materialized view mv1
-POSTHOOK: type: DROP_MATERIALIZED_VIEW
-POSTHOOK: Input: default@mv1
-POSTHOOK: Output: default@mv1
-PREHOOK: query: create materialized view mv1 enable rewrite as
-select empid, emps.deptno, count(*) as c, sum(empid) as s
-from emps join depts using (deptno)
-group by empid, emps.deptno
-PREHOOK: type: CREATE_MATERIALIZED_VIEW
-PREHOOK: Input: default@depts
-PREHOOK: Input: default@emps
-PREHOOK: Output: database:default
-PREHOOK: Output: default@mv1
-POSTHOOK: query: create materialized view mv1 enable rewrite as
-select empid, emps.deptno, count(*) as c, sum(empid) as s
-from emps join depts using (deptno)
-group by empid, emps.deptno
-POSTHOOK: type: CREATE_MATERIALIZED_VIEW
-POSTHOOK: Input: default@depts
-POSTHOOK: Input: default@emps
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@mv1
-PREHOOK: query: analyze table mv1 compute statistics for columns
-PREHOOK: type: QUERY
-PREHOOK: Input: default@mv1
-PREHOOK: Output: default@mv1
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1 compute statistics for columns
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@mv1
-POSTHOOK: Output: default@mv1
-#### A masked pattern was here ####
-PREHOOK: query: explain
-select depts.deptno, count(*) as c, sum(empid) as s
-from emps join depts using (deptno)
-group by depts.deptno
-PREHOOK: type: QUERY
-POSTHOOK: query: explain
-select depts.deptno, count(*) as c, sum(empid) as s
-from emps join depts using (deptno)
-group by depts.deptno
-POSTHOOK: type: QUERY
-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: default.mv1
- Statistics: Num rows: 4 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: deptno (type: int), c (type: bigint), s (type: bigint)
- outputColumnNames: deptno, c, s
- Statistics: Num rows: 4 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: $sum0(c), sum(s)
- keys: deptno (type: int)
- mode: hash
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col1 (type: bigint), _col2 (type: bigint)
- Reduce Operator Tree:
- Group By Operator
- aggregations: $sum0(VALUE._col0), sum(VALUE._col1)
- keys: KEY._col0 (type: int)
- mode: mergepartial
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
- 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 depts.deptno, count(*) as c, sum(empid) as s
-from emps join depts using (deptno)
-group by depts.deptno
-PREHOOK: type: QUERY
-PREHOOK: Input: default@depts
-PREHOOK: Input: default@emps
-PREHOOK: Input: default@mv1
-#### A masked pattern was here ####
-POSTHOOK: query: select depts.deptno, count(*) as c, sum(empid) as s
-from emps join depts using (deptno)
-group by depts.deptno
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@depts
-POSTHOOK: Input: default@emps
-POSTHOOK: Input: default@mv1
-#### A masked pattern was here ####
-10 4 470
-20 1 200
-PREHOOK: query: drop materialized view mv1
-PREHOOK: type: DROP_MATERIALIZED_VIEW
-PREHOOK: Input: default@mv1
-PREHOOK: Output: default@mv1
-POSTHOOK: query: drop materialized view mv1
-POSTHOOK: type: DROP_MATERIALIZED_VIEW
-POSTHOOK: Input: default@mv1
-POSTHOOK: Output: default@mv1
-PREHOOK: query: create materialized view mv1 enable rewrite as
-select empid, emps.deptno, count(*) as c, sum(empid) as s
-from emps join depts using (deptno)
-where emps.deptno >= 10 group by empid, emps.deptno
-PREHOOK: type: CREATE_MATERIALIZED_VIEW
-PREHOOK: Input: default@depts
-PREHOOK: Input: default@emps
-PREHOOK: Output: database:default
-PREHOOK: Output: default@mv1
-POSTHOOK: query: create materialized view mv1 enable rewrite as
-select empid, emps.deptno, count(*) as c, sum(empid) as s
-from emps join depts using (deptno)
-where emps.deptno >= 10 group by empid, emps.deptno
-POSTHOOK: type: CREATE_MATERIALIZED_VIEW
-POSTHOOK: Input: default@depts
-POSTHOOK: Input: default@emps
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@mv1
-PREHOOK: query: analyze table mv1 compute statistics for columns
-PREHOOK: type: QUERY
-PREHOOK: Input: default@mv1
-PREHOOK: Output: default@mv1
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1 compute statistics for columns
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@mv1
-POSTHOOK: Output: default@mv1
-#### A masked pattern was here ####
-PREHOOK: query: explain
-select depts.deptno, sum(empid) as s
-from emps join depts using (deptno)
-where emps.deptno > 10 group by depts.deptno
-PREHOOK: type: QUERY
-POSTHOOK: query: explain
-select depts.deptno, sum(empid) as s
-from emps join depts using (deptno)
-where emps.deptno > 10 group by depts.deptno
-POSTHOOK: type: QUERY
-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: default.mv1
- Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator
- predicate: (deptno > 10) (type: boolean)
- Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: sum(s)
- keys: deptno (type: int)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col1 (type: bigint)
- Reduce Operator Tree:
- Group By Operator
- aggregations: sum(VALUE._col0)
- keys: KEY._col0 (type: int)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
- 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 depts.deptno, sum(empid) as s
-from emps join depts using (deptno)
-where emps.deptno > 10 group by depts.deptno
-PREHOOK: type: QUERY
-PREHOOK: Input: default@depts
-PREHOOK: Input: default@emps
-PREHOOK: Input: default@mv1
-#### A masked pattern was here ####
-POSTHOOK: query: select depts.deptno, sum(empid) as s
-from emps join depts using (deptno)
-where emps.deptno > 10 group by depts.deptno
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@depts
-POSTHOOK: Input: default@emps
-POSTHOOK: Input: default@mv1
-#### A masked pattern was here ####
-20 200
-PREHOOK: query: drop materialized view mv1
-PREHOOK: type: DROP_MATERIALIZED_VIEW
-PREHOOK: Input: default@mv1
-PREHOOK: Output: default@mv1
-POSTHOOK: query: drop materialized view mv1
-POSTHOOK: type: DROP_MATERIALIZED_VIEW
-POSTHOOK: Input: default@mv1
-POSTHOOK: Output: default@mv1
-PREHOOK: query: create materialized view mv1 enable rewrite as
-select empid, depts.deptno, count(*) + 1 as c, sum(empid) as s
-from emps join depts using (deptno)
-where depts.deptno >= 10 group by empid, depts.deptno
-PREHOOK: type: CREATE_MATERIALIZED_VIEW
-PREHOOK: Input: default@depts
-PREHOOK: Input: default@emps
-PREHOOK: Output: database:default
-PREHOOK: Output: default@mv1
-POSTHOOK: query: create materialized view mv1 enable rewrite as
-select empid, depts.deptno, count(*) + 1 as c, sum(empid) as s
-from emps join depts using (deptno)
-where depts.deptno >= 10 group by empid, depts.deptno
-POSTHOOK: type: CREATE_MATERIALIZED_VIEW
-POSTHOOK: Input: default@depts
-POSTHOOK: Input: default@emps
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@mv1
-PREHOOK: query: analyze table mv1 compute statistics for columns
-PREHOOK: type: QUERY
-PREHOOK: Input: default@mv1
-PREHOOK: Output: default@mv1
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1 compute statistics for columns
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@mv1
-POSTHOOK: Output: default@mv1
-#### A masked pattern was here ####
-PREHOOK: query: explain
-select depts.deptno, sum(empid) + 1 as s
-from emps join depts using (deptno)
-where depts.deptno > 10 group by depts.deptno
-PREHOOK: type: QUERY
-POSTHOOK: query: explain
-select depts.deptno, sum(empid) + 1 as s
-from emps join depts using (deptno)
-where depts.deptno > 10 group by depts.deptno
-POSTHOOK: type: QUERY
-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: default.mv1
- Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator
- predicate: (deptno > 10) (type: boolean)
- Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: deptno (type: int), s (type: bigint)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: sum(_col1)
- keys: _col0 (type: int)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col1 (type: bigint)
- Reduce Operator Tree:
- Group By Operator
- aggregations: sum(VALUE._col0)
- keys: KEY._col0 (type: int)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col0 (type: int), (_col1 + 1L) (type: bigint)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
- 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 depts.deptno, sum(empid) + 1 as s
-from emps join depts using (deptno)
-where depts.deptno > 10 group by depts.deptno
-PREHOOK: type: QUERY
-PREHOOK: Input: default@depts
-PREHOOK: Input: default@emps
-PREHOOK: Input: default@mv1
-#### A masked pattern was here ####
-POSTHOOK: query: select depts.deptno, sum(empid) + 1 as s
-from emps join depts using (deptno)
-where depts.deptno > 10 group by depts.deptno
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@depts
-POSTHOOK: Input: default@emps
-POSTHOOK: Input: default@mv1
-#### A masked pattern was here ####
-20 201
-PREHOOK: query: drop materialized view mv1
-PREHOOK: type: DROP_MATERIALIZED_VIEW
-PREHOOK: Input: default@mv1
-PREHOOK: Output: default@mv1
-POSTHOOK: query: drop materialized view mv1
-POSTHOOK: type: DROP_MATERIALIZED_VIEW
-POSTHOOK: Input: default@mv1
-POSTHOOK: Output: default@mv1
-PREHOOK: query: create materialized view mv1 enable rewrite as
-select depts.name, sum(salary) as s
-from emps
-join depts on (emps.deptno = depts.deptno)
-group by depts.name
-PREHOOK: type: CREATE_MATERIALIZED_VIEW
-PREHOOK: Input: default@depts
-PREHOOK: Input: default@emps
-PREHOOK: Output: database:default
-PREHOOK: Output: default@mv1
-POSTHOOK: query: create materialized view mv1 enable rewrite as
-select depts.name, sum(salary) as s
-from emps
-join depts on (emps.deptno = depts.deptno)
-group by depts.name
-POSTHOOK: type: CREATE_MATERIALIZED_VIEW
-POSTHOOK: Input: default@depts
-POSTHOOK: Input: default@emps
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@mv1
-PREHOOK: query: analyze table mv1 compute statistics for columns
-PREHOOK: type: QUERY
-PREHOOK: Input: default@mv1
-PREHOOK: Output: default@mv1
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1 compute statistics for columns
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@mv1
-POSTHOOK: Output: default@mv1
-#### A masked pattern was here ####
-PREHOOK: query: explain
-select dependents.empid, sum(salary) as s
-from emps
-join depts on (emps.deptno = depts.deptno)
-join dependents on (depts.name = dependents.name)
-group by dependents.empid
-PREHOOK: type: QUERY
-POSTHOOK: query: explain
-select dependents.empid, sum(salary) as s
-from emps
-join depts on (emps.deptno = depts.deptno)
-join dependents on (depts.name = dependents.name)
-group by dependents.empid
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-2 depends on stages: Stage-1
- Stage-0 depends on stages: Stage-2
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: default.mv1
- Statistics: Num rows: 2 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator
- predicate: name is not null (type: boolean)
- Statistics: Num rows: 2 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: name (type: varchar(256)), s (type: double)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 2 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: varchar(256))
- sort order: +
- Map-reduce partition columns: _col0 (type: varchar(256))
- Statistics: Num rows: 2 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col1 (type: double)
- TableScan
- alias: dependents
- Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator
- predicate: name is not null (type: boolean)
- Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: empid (type: int), name (type: varchar(256))
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col1 (type: varchar(256))
- sort order: +
- Map-reduce partition columns: _col1 (type: varchar(256))
- Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: int)
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: varchar(256))
- 1 _col1 (type: varchar(256))
- outputColumnNames: _col1, _col2
- Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: sum(_col1)
- keys: _col2 (type: int)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col1 (type: double)
- Reduce Operator Tree:
- Group By Operator
- aggregations: sum(VALUE._col0)
- keys: KEY._col0 (type: int)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
- 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 dependents.empid, sum(salary) as s
-from emps
-join depts on (emps.deptno = depts.deptno)
-join dependents on (depts.name = dependents.name)
-group by dependents.empid
-PREHOOK: type: QUERY
-PREHOOK: Input: default@dependents
-PREHOOK: Input: default@depts
-PREHOOK: Input: default@emps
-PREHOOK: Input: default@mv1
-#### A masked pattern was here ####
-POSTHOOK: query: select dependents.empid, sum(salary) as s
-from emps
-join depts on (emps.deptno = depts.deptno)
-join dependents on (depts.name = dependents.name)
-group by dependents.empid
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@dependents
-POSTHOOK: Input: default@depts
-POSTHOOK: Input: default@emps
-POSTHOOK: Input: default@mv1
-#### A masked pattern was here ####
-PREHOOK: query: drop materialized view mv1
-PREHOOK: type: DROP_MATERIALIZED_VIEW
-PREHOOK: Input: default@mv1
-PREHOOK: Output: default@mv1
-POSTHOOK: query: drop materialized view mv1
-POSTHOOK: type: DROP_MATERIALIZED_VIEW
-POSTHOOK: Input: default@mv1
-POSTHOOK: Output: default@mv1
-PREHOOK: query: create materialized view mv1 enable rewrite as
-select dependents.empid, emps.deptno, count(distinct salary) as s
-from emps
-join dependents on (emps.empid = dependents.empid)
-group by dependents.empid, emps.deptno
-PREHOOK: type: CREATE_MATERIALIZED_VIEW
-PREHOOK: Input: default@dependents
-PREHOOK: Input: default@emps
-PREHOOK: Output: database:default
-PREHOOK: Output: default@mv1
-POSTHOOK: query: create materialized view mv1 enable rewrite as
-select dependents.empid, emps.deptno, count(distinct salary) as s
-from emps
-join dependents on (emps.empid = dependents.empid)
-group by dependents.empid, emps.deptno
-POSTHOOK: type: CREATE_MATERIALIZED_VIEW
-POSTHOOK: Input: default@dependents
-POSTHOOK: Input: default@emps
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@mv1
-PREHOOK: query: analyze table mv1 compute statistics for columns
-PREHOOK: type: QUERY
-PREHOOK: Input: default@mv1
-PREHOOK: Output: default@mv1
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1 compute statistics for columns
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@mv1
-POSTHOOK: Output: default@mv1
-#### A masked pattern was here ####
-PREHOOK: query: explain
-select emps.deptno, count(distinct salary) as s
-from emps
-join dependents on (emps.empid = dependents.empid)
-group by dependents.empid, emps.deptno
-PREHOOK: type: QUERY
-POSTHOOK: query: explain
-select emps.deptno, count(distinct salary) as s
-from emps
-join dependents on (emps.empid = dependents.empid)
-group by dependents.empid, emps.deptno
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-0 is a root stage
-
-STAGE PLANS:
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- TableScan
- alias: default.mv1
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: deptno (type: int), s (type: bigint)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
- ListSink
-
-PREHOOK: query: select emps.deptno, count(distinct salary) as s
-from emps
-join dependents on (emps.empid = dependents.empid)
-group by dependents.empid, emps.deptno
-PREHOOK: type: QUERY
-PREHOOK: Input: default@dependents
-PREHOOK: Input: default@emps
-PREHOOK: Input: default@mv1
-#### A masked pattern was here ####
-POSTHOOK: query: select emps.deptno, count(distinct salary) as s
-from emps
-join dependents on (emps.empid = dependents.empid)
-group by dependents.empid, emps.deptno
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@dependents
-POSTHOOK: Input: default@emps
-POSTHOOK: Input: default@mv1
-#### A masked pattern was here ####
-PREHOOK: query: drop materialized view mv1
-PREHOOK: type: DROP_MATERIALIZED_VIEW
-PREHOOK: Input: default@mv1
-PREHOOK: Output: default@mv1
-POSTHOOK: query: drop materialized view mv1
-POSTHOOK: type: DROP_MATERIALIZED_VIEW
-POSTHOOK: Input: default@mv1
-POSTHOOK: Output: default@mv1