Added: hive/trunk/ql/src/test/results/clientpositive/skewjoin_mapjoin7.q.out URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/skewjoin_mapjoin7.q.out?rev=1635630&view=auto ============================================================================== --- hive/trunk/ql/src/test/results/clientpositive/skewjoin_mapjoin7.q.out (added) +++ hive/trunk/ql/src/test/results/clientpositive/skewjoin_mapjoin7.q.out Thu Oct 30 22:23:40 2014 @@ -0,0 +1,363 @@ +PREHOOK: query: CREATE TABLE T1(key STRING, val STRING) +SKEWED BY (key) ON ((2)) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T1 +POSTHOOK: query: CREATE TABLE T1(key STRING, val STRING) +SKEWED BY (key) ON ((2)) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T1 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t1 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t1 +PREHOOK: query: CREATE TABLE T2(key STRING, val STRING) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T2 +POSTHOOK: query: CREATE TABLE T2(key STRING, val STRING) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T2 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t2 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t2 +PREHOOK: query: -- copy from skewjoinopt11 +-- test compile time skew join and auto map join +-- This test is to verify the skew join compile optimization when the join is followed +-- by a union. Both sides of a union consist of a join, which should have used +-- skew join compile time optimization. +-- adding an order by at the end to make the results deterministic + +EXPLAIN +select * from +( + select a.key, a.val as val1, b.val as val2 from T1 a join T2 b on a.key = b.key + union all + select a.key, a.val as val1, b.val as val2 from T1 a join T2 b on a.key = b.key +) subq1 +PREHOOK: type: QUERY +POSTHOOK: query: -- copy from skewjoinopt11 +-- test compile time skew join and auto map join +-- This test is to verify the skew join compile optimization when the join is followed +-- by a union. Both sides of a union consist of a join, which should have used +-- skew join compile time optimization. +-- adding an order by at the end to make the results deterministic + +EXPLAIN +select * from +( + select a.key, a.val as val1, b.val as val2 from T1 a join T2 b on a.key = b.key + union all + select a.key, a.val as val1, b.val as val2 from T1 a join T2 b on a.key = b.key +) subq1 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-16 is a root stage + Stage-2 depends on stages: Stage-16 + Stage-3 depends on stages: Stage-2, Stage-8 + Stage-17 is a root stage + Stage-8 depends on stages: Stage-17 + Stage-0 depends on stages: Stage-3 + +STAGE PLANS: + Stage: Stage-16 + Map Reduce Local Work + Alias -> Map Local Tables: + null-subquery2:subq1-subquery2:a + Fetch Operator + limit: -1 + subquery1:a + Fetch Operator + limit: -1 + Alias -> Map Local Operator Tree: + null-subquery2:subq1-subquery2:a + TableScan + alias: a + Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: (key is not null and (key = '2')) (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 {val} + 1 {val} + keys: + 0 key (type: string) + 1 key (type: string) + subquery1:a + TableScan + alias: a + Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: (key is not null and (not (key = '2'))) (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 {val} + 1 {val} + keys: + 0 key (type: string) + 1 key (type: string) + + Stage: Stage-2 + Map Reduce + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: (key is not null and (not (key = '2'))) (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {key} {val} + 1 {val} + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: _col0, _col1, _col6 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Union + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + SELECT * : (no compute) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + 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 + TableScan + alias: b + Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: (key is not null and (key = '2')) (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {key} {val} + 1 {val} + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: _col0, _col1, _col6 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Union + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + SELECT * : (no compute) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + 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 + Local Work: + Map Reduce Local Work + + Stage: Stage-3 + Map Reduce + Map Operator Tree: + TableScan + Union + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + 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 + TableScan + Union + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + 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-17 + Map Reduce Local Work + Alias -> Map Local Tables: + null-subquery1:subq1-subquery1:a + Fetch Operator + limit: -1 + subquery2:a + Fetch Operator + limit: -1 + Alias -> Map Local Operator Tree: + null-subquery1:subq1-subquery1:a + TableScan + alias: a + Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: (key is not null and (key = '2')) (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 {val} + 1 {val} + keys: + 0 key (type: string) + 1 key (type: string) + subquery2:a + TableScan + alias: a + Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: (key is not null and (not (key = '2'))) (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 {val} + 1 {val} + keys: + 0 key (type: string) + 1 key (type: string) + + Stage: Stage-8 + Map Reduce + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: (key is not null and (key = '2')) (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {key} {val} + 1 {val} + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: _col0, _col1, _col6 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Union + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + SELECT * : (no compute) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + 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 + TableScan + alias: b + Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: (key is not null and (not (key = '2'))) (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {key} {val} + 1 {val} + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: _col0, _col1, _col6 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Union + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + SELECT * : (no compute) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + 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 + Local Work: + Map Reduce Local Work + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select * from +( + select a.key, a.val as val1, b.val as val2 from T1 a join T2 b on a.key = b.key + union all + select a.key, a.val as val1, b.val as val2 from T1 a join T2 b on a.key = b.key +) subq1 +ORDER BY key, val1, val2 +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +PREHOOK: Input: default@t2 +#### A masked pattern was here #### +POSTHOOK: query: select * from +( + select a.key, a.val as val1, b.val as val2 from T1 a join T2 b on a.key = b.key + union all + select a.key, a.val as val1, b.val as val2 from T1 a join T2 b on a.key = b.key +) subq1 +ORDER BY key, val1, val2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +POSTHOOK: Input: default@t2 +#### A masked pattern was here #### +2 12 22 +2 12 22 +3 13 13 +3 13 13 +8 18 18 +8 18 18 +8 18 18 +8 18 18 +8 28 18 +8 28 18 +8 28 18 +8 28 18
Added: hive/trunk/ql/src/test/results/clientpositive/skewjoin_mapjoin8.q.out URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/skewjoin_mapjoin8.q.out?rev=1635630&view=auto ============================================================================== --- hive/trunk/ql/src/test/results/clientpositive/skewjoin_mapjoin8.q.out (added) +++ hive/trunk/ql/src/test/results/clientpositive/skewjoin_mapjoin8.q.out Thu Oct 30 22:23:40 2014 @@ -0,0 +1,197 @@ +PREHOOK: query: CREATE TABLE T1(key STRING, val STRING) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T1 +POSTHOOK: query: CREATE TABLE T1(key STRING, val STRING) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T1 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t1 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t1 +PREHOOK: query: CREATE TABLE T2(key STRING, val STRING) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T2 +POSTHOOK: query: CREATE TABLE T2(key STRING, val STRING) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T2 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t2 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t2 +PREHOOK: query: CREATE TABLE T3(key STRING, val STRING) +SKEWED BY (val) ON ((12)) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T3 +POSTHOOK: query: CREATE TABLE T3(key STRING, val STRING) +SKEWED BY (val) ON ((12)) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T3 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T3.txt' INTO TABLE T3 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t3 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T3.txt' INTO TABLE T3 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t3 +PREHOOK: query: -- copy from skewjoinopt13 +-- test compile time skew join and auto map join +-- This test is for skewed join compile time optimization for more than 2 tables. +-- The join key for table 3 is different from the join key used for joining +-- tables 1 and 2. Table 3 is skewed, but since one of the join sources for table +-- 3 consist of a sub-query which contains a join, the compile time skew join +-- optimization is not performed +-- adding a order by at the end to make the results deterministic + +EXPLAIN +select * +from +T1 a join T2 b on a.key = b.key +join T3 c on a.val = c.val +PREHOOK: type: QUERY +POSTHOOK: query: -- copy from skewjoinopt13 +-- test compile time skew join and auto map join +-- This test is for skewed join compile time optimization for more than 2 tables. +-- The join key for table 3 is different from the join key used for joining +-- tables 1 and 2. Table 3 is skewed, but since one of the join sources for table +-- 3 consist of a sub-query which contains a join, the compile time skew join +-- optimization is not performed +-- adding a order by at the end to make the results deterministic + +EXPLAIN +select * +from +T1 a join T2 b on a.key = b.key +join T3 c on a.val = c.val +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-7 is a root stage + Stage-5 depends on stages: Stage-7 + Stage-0 depends on stages: Stage-5 + +STAGE PLANS: + Stage: Stage-7 + Map Reduce Local Work + Alias -> Map Local Tables: + a + Fetch Operator + limit: -1 + c + Fetch Operator + limit: -1 + Alias -> Map Local Operator Tree: + a + TableScan + alias: a + Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: (key is not null and val is not null) (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 {val} + 1 {key} {val} + keys: + 0 key (type: string) + 1 key (type: string) + c + TableScan + alias: c + Statistics: Num rows: 0 Data size: 20 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: val is not null (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 {_col0} {_col1} {_col5} {_col6} + 1 {key} + keys: + 0 _col1 (type: string) + 1 val (type: string) + + Stage: Stage-5 + Map Reduce + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {key} {val} + 1 {key} {val} + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: _col0, _col1, _col5, _col6 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} {_col1} {_col5} {_col6} + 1 {key} {val} + keys: + 0 _col1 (type: string) + 1 val (type: string) + outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + 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 + Local Work: + Map Reduce Local Work + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select * +from +T1 a join T2 b on a.key = b.key +join T3 c on a.val = c.val +order by a.key, b.key, c.key, a.val, b.val, c.val +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +PREHOOK: Input: default@t2 +PREHOOK: Input: default@t3 +#### A masked pattern was here #### +POSTHOOK: query: select * +from +T1 a join T2 b on a.key = b.key +join T3 c on a.val = c.val +order by a.key, b.key, c.key, a.val, b.val, c.val +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +POSTHOOK: Input: default@t2 +POSTHOOK: Input: default@t3 +#### A masked pattern was here #### +2 12 2 22 2 12 Added: hive/trunk/ql/src/test/results/clientpositive/skewjoin_mapjoin9.q.out URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/skewjoin_mapjoin9.q.out?rev=1635630&view=auto ============================================================================== --- hive/trunk/ql/src/test/results/clientpositive/skewjoin_mapjoin9.q.out (added) +++ hive/trunk/ql/src/test/results/clientpositive/skewjoin_mapjoin9.q.out Thu Oct 30 22:23:40 2014 @@ -0,0 +1,267 @@ +PREHOOK: query: CREATE TABLE T1(key STRING, val STRING) +SKEWED BY (key) ON ((2)) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T1 +POSTHOOK: query: CREATE TABLE T1(key STRING, val STRING) +SKEWED BY (key) ON ((2)) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T1 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t1 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t1 +PREHOOK: query: CREATE TABLE T2(key STRING, val STRING) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T2 +POSTHOOK: query: CREATE TABLE T2(key STRING, val STRING) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T2 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t2 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t2 +PREHOOK: query: CREATE TABLE T3(key STRING, val STRING) +SKEWED BY (val) ON ((12)) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T3 +POSTHOOK: query: CREATE TABLE T3(key STRING, val STRING) +SKEWED BY (val) ON ((12)) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T3 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T3.txt' INTO TABLE T3 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t3 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T3.txt' INTO TABLE T3 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t3 +PREHOOK: query: -- copy from skewjoinopt14 +-- test compile time skew join and auto map join +-- This test is for skewed join compile time optimization for more than 2 tables. +-- The join key for table 3 is different from the join key used for joining +-- tables 1 and 2. Tables 1 and 3 are skewed. Since one of the join sources for table +-- 3 consist of a sub-query which contains a join, the compile time skew join +-- optimization is not enabled for table 3, but it is used for the first join between +-- tables 1 and 2 +-- adding a order by at the end to make the results deterministic + +EXPLAIN +select * +from +T1 a join T2 b on a.key = b.key +join T3 c on a.val = c.val +PREHOOK: type: QUERY +POSTHOOK: query: -- copy from skewjoinopt14 +-- test compile time skew join and auto map join +-- This test is for skewed join compile time optimization for more than 2 tables. +-- The join key for table 3 is different from the join key used for joining +-- tables 1 and 2. Tables 1 and 3 are skewed. Since one of the join sources for table +-- 3 consist of a sub-query which contains a join, the compile time skew join +-- optimization is not enabled for table 3, but it is used for the first join between +-- tables 1 and 2 +-- adding a order by at the end to make the results deterministic + +EXPLAIN +select * +from +T1 a join T2 b on a.key = b.key +join T3 c on a.val = c.val +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-10 is a root stage + Stage-7 depends on stages: Stage-10 + Stage-0 depends on stages: Stage-7 + +STAGE PLANS: + Stage: Stage-10 + Map Reduce Local Work + Alias -> Map Local Tables: + a + Fetch Operator + limit: -1 + c + Fetch Operator + limit: -1 + subquery1:a + Fetch Operator + limit: -1 + Alias -> Map Local Operator Tree: + a + TableScan + alias: a + Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: ((key is not null and val is not null) and (key = '2')) (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 {val} + 1 {key} {val} + keys: + 0 key (type: string) + 1 key (type: string) + c + TableScan + alias: c + Statistics: Num rows: 0 Data size: 20 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: val is not null (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 {_col0} {_col1} {_col5} {_col6} + 1 {key} + keys: + 0 _col1 (type: string) + 1 val (type: string) + subquery1:a + TableScan + alias: a + Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: ((key is not null and val is not null) and (not (key = '2'))) (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 {val} + 1 {key} {val} + keys: + 0 key (type: string) + 1 key (type: string) + + Stage: Stage-7 + Map Reduce + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: (key is not null and (not (key = '2'))) (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {key} {val} + 1 {key} {val} + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: _col0, _col1, _col5, _col6 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Union + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + SELECT * : (no compute) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} {_col1} {_col5} {_col6} + 1 {key} {val} + keys: + 0 _col1 (type: string) + 1 val (type: string) + outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + 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 + TableScan + alias: b + Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: (key is not null and (key = '2')) (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {key} {val} + 1 {key} {val} + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: _col0, _col1, _col5, _col6 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Union + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + SELECT * : (no compute) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} {_col1} {_col5} {_col6} + 1 {key} {val} + keys: + 0 _col1 (type: string) + 1 val (type: string) + outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + 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 + Local Work: + Map Reduce Local Work + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select * +from +T1 a join T2 b on a.key = b.key +join T3 c on a.val = c.val +order by a.key, b.key, a.val, b.val +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +PREHOOK: Input: default@t2 +PREHOOK: Input: default@t3 +#### A masked pattern was here #### +POSTHOOK: query: select * +from +T1 a join T2 b on a.key = b.key +join T3 c on a.val = c.val +order by a.key, b.key, a.val, b.val +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +POSTHOOK: Input: default@t2 +POSTHOOK: Input: default@t3 +#### A masked pattern was here #### +2 12 2 22 2 12
