PREHOOK: query: create table if not exists emp ( lastname string, deptid int, locid int ) row format delimited fields terminated by '|' stored as textfile PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@emp POSTHOOK: query: create table if not exists emp ( lastname string, deptid int, locid int ) row format delimited fields terminated by '|' stored as textfile POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@emp PREHOOK: query: create table if not exists dept ( deptid int, deptname string ) row format delimited fields terminated by '|' stored as textfile PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@dept POSTHOOK: query: create table if not exists dept ( deptid int, deptname string ) row format delimited fields terminated by '|' stored as textfile POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@dept PREHOOK: query: create table if not exists loc ( state string, locid int, zip bigint, year int ) row format delimited fields terminated by '|' stored as textfile PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@loc POSTHOOK: query: create table if not exists loc ( state string, locid int, zip bigint, year int ) row format delimited fields terminated by '|' stored as textfile POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@loc PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/emp.txt' OVERWRITE INTO TABLE emp PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@emp POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/emp.txt' OVERWRITE INTO TABLE emp POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@emp PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/dept.txt' OVERWRITE INTO TABLE dept PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@dept POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/dept.txt' OVERWRITE INTO TABLE dept POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@dept PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/loc.txt' OVERWRITE INTO TABLE loc PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@loc POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/loc.txt' OVERWRITE INTO TABLE loc POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@loc PREHOOK: query: analyze table emp compute statistics PREHOOK: type: QUERY PREHOOK: Input: default@emp PREHOOK: Output: default@emp POSTHOOK: query: analyze table emp compute statistics POSTHOOK: type: QUERY POSTHOOK: Input: default@emp POSTHOOK: Output: default@emp PREHOOK: query: analyze table dept compute statistics PREHOOK: type: QUERY PREHOOK: Input: default@dept PREHOOK: Output: default@dept POSTHOOK: query: analyze table dept compute statistics POSTHOOK: type: QUERY POSTHOOK: Input: default@dept POSTHOOK: Output: default@dept PREHOOK: query: analyze table loc compute statistics PREHOOK: type: QUERY PREHOOK: Input: default@loc PREHOOK: Output: default@loc POSTHOOK: query: analyze table loc compute statistics POSTHOOK: type: QUERY POSTHOOK: Input: default@loc POSTHOOK: Output: default@loc PREHOOK: query: analyze table emp compute statistics for columns lastname,deptid,locid PREHOOK: type: QUERY PREHOOK: Input: default@emp #### A masked pattern was here #### POSTHOOK: query: analyze table emp compute statistics for columns lastname,deptid,locid POSTHOOK: type: QUERY POSTHOOK: Input: default@emp #### A masked pattern was here #### PREHOOK: query: analyze table dept compute statistics for columns deptname,deptid PREHOOK: type: QUERY PREHOOK: Input: default@dept #### A masked pattern was here #### POSTHOOK: query: analyze table dept compute statistics for columns deptname,deptid POSTHOOK: type: QUERY POSTHOOK: Input: default@dept #### A masked pattern was here #### PREHOOK: query: analyze table loc compute statistics for columns state,locid,zip,year PREHOOK: type: QUERY PREHOOK: Input: default@loc #### A masked pattern was here #### POSTHOOK: query: analyze table loc compute statistics for columns state,locid,zip,year POSTHOOK: type: QUERY POSTHOOK: Input: default@loc #### A masked pattern was here #### PREHOOK: query: -- number of rows -- emp - 48 -- dept - 6 -- loc - 8 -- count distincts for relevant columns (since count distinct values are approximate in some cases count distint values will be greater than number of rows) -- emp.deptid - 3 -- emp.lastname - 6 -- emp.locid - 7 -- dept.deptid - 7 -- dept.deptname - 6 -- loc.locid - 7 -- loc.state - 6 -- 2 relations, 1 attribute -- Expected output rows: (48*6)/max(3,7) = 41 explain select * from emp e join dept d on (e.deptid = d.deptid) PREHOOK: type: QUERY POSTHOOK: query: -- number of rows -- emp - 48 -- dept - 6 -- loc - 8 -- count distincts for relevant columns (since count distinct values are approximate in some cases count distint values will be greater than number of rows) -- emp.deptid - 3 -- emp.lastname - 6 -- emp.locid - 7 -- dept.deptid - 7 -- dept.deptname - 6 -- loc.locid - 7 -- loc.state - 6 -- 2 relations, 1 attribute -- Expected output rows: (48*6)/max(3,7) = 41 explain select * from emp e join dept d on (e.deptid = d.deptid) 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: e Statistics: Num rows: 48 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: deptid is not null (type: boolean) Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: lastname (type: string), deptid (type: int), locid (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col2 (type: int) TableScan alias: d Statistics: Num rows: 6 Data size: 62 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: deptid is not null (type: boolean) Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: deptid (type: int), deptname (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 570 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: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 41 Data size: 4059 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 41 Data size: 4059 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false Statistics: Num rows: 41 Data size: 4059 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: ListSink PREHOOK: query: -- 2 relations, 2 attributes -- Expected output rows: (48*6)/(max(3,7) * max(6,6)) = 6 explain select * from emp,dept where emp.deptid = dept.deptid and emp.lastname = dept.deptname PREHOOK: type: QUERY POSTHOOK: query: -- 2 relations, 2 attributes -- Expected output rows: (48*6)/(max(3,7) * max(6,6)) = 6 explain select * from emp,dept where emp.deptid = dept.deptid and emp.lastname = dept.deptname 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: emp Statistics: Num rows: 48 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (deptid is not null and lastname is not null) (type: boolean) Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: lastname (type: string), deptid (type: int), locid (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int), _col0 (type: string) sort order: ++ Map-reduce partition columns: _col1 (type: int), _col0 (type: string) Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: int) TableScan alias: dept Statistics: Num rows: 6 Data size: 62 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (deptid is not null and deptname is not null) (type: boolean) Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: deptid (type: int), deptname (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: 0 _col1 (type: int), _col0 (type: string) 1 _col0 (type: int), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 6 Data size: 594 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 6 Data size: 594 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false Statistics: Num rows: 6 Data size: 594 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: ListSink PREHOOK: query: explain select * from emp e join dept d on (e.deptid = d.deptid and e.lastname = d.deptname) PREHOOK: type: QUERY POSTHOOK: query: explain select * from emp e join dept d on (e.deptid = d.deptid and e.lastname = d.deptname) 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: e Statistics: Num rows: 48 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (deptid is not null and lastname is not null) (type: boolean) Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: lastname (type: string), deptid (type: int), locid (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int), _col0 (type: string) sort order: ++ Map-reduce partition columns: _col1 (type: int), _col0 (type: string) Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: int) TableScan alias: d Statistics: Num rows: 6 Data size: 62 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (deptid is not null and deptname is not null) (type: boolean) Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: deptid (type: int), deptname (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: 0 _col1 (type: int), _col0 (type: string) 1 _col0 (type: int), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 6 Data size: 594 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 6 Data size: 594 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false Statistics: Num rows: 6 Data size: 594 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: ListSink PREHOOK: query: -- 2 relations, 3 attributes -- Expected output rows: (48*6)/(max(3,7) * max(6,6) * max(6,6)) = 1 explain select * from emp,dept where emp.deptid = dept.deptid and emp.lastname = dept.deptname and dept.deptname = emp.lastname PREHOOK: type: QUERY POSTHOOK: query: -- 2 relations, 3 attributes -- Expected output rows: (48*6)/(max(3,7) * max(6,6) * max(6,6)) = 1 explain select * from emp,dept where emp.deptid = dept.deptid and emp.lastname = dept.deptname and dept.deptname = emp.lastname 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: emp Statistics: Num rows: 48 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (deptid is not null and lastname is not null) (type: boolean) Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: lastname (type: string), deptid (type: int), locid (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int), _col0 (type: string), _col0 (type: string) sort order: +++ Map-reduce partition columns: _col1 (type: int), _col0 (type: string), _col0 (type: string) Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: int) TableScan alias: dept Statistics: Num rows: 6 Data size: 62 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (deptid is not null and deptname is not null) (type: boolean) Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: deptid (type: int), deptname (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string), _col1 (type: string) sort order: +++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string), _col1 (type: string) Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: 0 _col1 (type: int), _col0 (type: string), _col0 (type: string) 1 _col0 (type: int), _col1 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 11 Data size: 1089 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 11 Data size: 1089 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false Statistics: Num rows: 11 Data size: 1089 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: ListSink PREHOOK: query: -- 3 relations, 1 attribute -- Expected output rows: (48*6*48)/top2largest(3,7,3) = 658 explain select * from emp e join dept d on (e.deptid = d.deptid) join emp e1 on (e.deptid = e1.deptid) PREHOOK: type: QUERY POSTHOOK: query: -- 3 relations, 1 attribute -- Expected output rows: (48*6*48)/top2largest(3,7,3) = 658 explain select * from emp e join dept d on (e.deptid = d.deptid) join emp e1 on (e.deptid = e1.deptid) 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: e Statistics: Num rows: 48 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: deptid is not null (type: boolean) Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: lastname (type: string), deptid (type: int), locid (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col2 (type: int) TableScan alias: e Statistics: Num rows: 48 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: deptid is not null (type: boolean) Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: lastname (type: string), deptid (type: int), locid (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col2 (type: int) TableScan alias: d Statistics: Num rows: 6 Data size: 62 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: deptid is not null (type: boolean) Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: deptid (type: int), deptname (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 570 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: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 Inner Join 0 to 2 keys: 0 _col1 (type: int) 1 _col0 (type: int) 2 _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 1536 Data size: 152064 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: string), _col5 (type: string), _col6 (type: int), _col7 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 1536 Data size: 152064 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false Statistics: Num rows: 1536 Data size: 152064 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: ListSink PREHOOK: query: -- Expected output rows: (48*6*8)/top2largest(3,7,7) = 47 explain select * from emp e join dept d on (e.deptid = d.deptid) join loc l on (e.deptid = l.locid) PREHOOK: type: QUERY POSTHOOK: query: -- Expected output rows: (48*6*8)/top2largest(3,7,7) = 47 explain select * from emp e join dept d on (e.deptid = d.deptid) join loc l on (e.deptid = l.locid) 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: e Statistics: Num rows: 48 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: deptid is not null (type: boolean) Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: lastname (type: string), deptid (type: int), locid (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col2 (type: int) TableScan alias: d Statistics: Num rows: 6 Data size: 62 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: deptid is not null (type: boolean) Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: deptid (type: int), deptname (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 570 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: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: l Statistics: Num rows: 8 Data size: 109 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: locid is not null (type: boolean) Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col2 (type: bigint), _col3 (type: int) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 Inner Join 0 to 2 keys: 0 _col1 (type: int) 1 _col0 (type: int) 2 _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 47 Data size: 4794 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: string), _col5 (type: string), _col6 (type: int), _col7 (type: bigint), _col8 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 47 Data size: 4794 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false Statistics: Num rows: 47 Data size: 4794 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: ListSink PREHOOK: query: -- 3 relations and 2 attribute -- Expected output rows: (48*6*8)/top2largest(3,7,7)*top2largest(6,6,6) = 1 explain select * from emp e join dept d on (e.deptid = d.deptid and e.lastname = d.deptname) join loc l on (e.deptid = l.locid and e.lastname = l.state) PREHOOK: type: QUERY POSTHOOK: query: -- 3 relations and 2 attribute -- Expected output rows: (48*6*8)/top2largest(3,7,7)*top2largest(6,6,6) = 1 explain select * from emp e join dept d on (e.deptid = d.deptid and e.lastname = d.deptname) join loc l on (e.deptid = l.locid and e.lastname = l.state) 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: e Statistics: Num rows: 48 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (deptid is not null and lastname is not null) (type: boolean) Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: lastname (type: string), deptid (type: int), locid (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int), _col0 (type: string) sort order: ++ Map-reduce partition columns: _col1 (type: int), _col0 (type: string) Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: int) TableScan alias: d Statistics: Num rows: 6 Data size: 62 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (deptid is not null and deptname is not null) (type: boolean) Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: deptid (type: int), deptname (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: l Statistics: Num rows: 8 Data size: 109 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (locid is not null and state is not null) (type: boolean) Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int), _col0 (type: string) sort order: ++ Map-reduce partition columns: _col1 (type: int), _col0 (type: string) Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint), _col3 (type: int) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 Inner Join 0 to 2 keys: 0 _col1 (type: int), _col0 (type: string) 1 _col0 (type: int), _col1 (type: string) 2 _col1 (type: int), _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: string), _col5 (type: string), _col6 (type: int), _col7 (type: bigint), _col8 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: ListSink