Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt14.q.out URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt14.q.out?rev=1634671&view=auto ============================================================================== --- hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt14.q.out (added) +++ hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt14.q.out Mon Oct 27 19:56:58 2014 @@ -0,0 +1,199 @@ +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: -- 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: -- 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-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 5 (GROUP PARTITION-LEVEL SORT, 1) + Reducer 3 <- Map 4 (GROUP PARTITION-LEVEL SORT, 1), Reducer 2 (GROUP PARTITION-LEVEL SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + 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 + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions: val (type: string) + Map 4 + Map Operator Tree: + 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 + Reduce Output Operator + key expressions: val (type: string) + sort order: + + Map-reduce partition columns: val (type: string) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions: key (type: string) + Map 5 + Map Operator Tree: + 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 + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions: val (type: string) + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col0, _col1, _col5, _col6 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions: _col0 (type: string), _col5 (type: string), _col6 (type: string) + Reducer 3 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {VALUE._col0} {KEY.reducesinkkey0} {VALUE._col4} {VALUE._col5} + 1 {VALUE._col0} {KEY.reducesinkkey0} + 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 + + 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
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt15.q.out URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt15.q.out?rev=1634671&view=auto ============================================================================== --- hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt15.q.out (added) +++ hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt15.q.out Mon Oct 27 19:56:58 2014 @@ -0,0 +1,464 @@ +PREHOOK: query: CREATE TABLE tmpT1(key STRING, val STRING) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@tmpT1 +POSTHOOK: query: CREATE TABLE tmpT1(key STRING, val STRING) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@tmpT1 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE tmpT1 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@tmpt1 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE tmpT1 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@tmpt1 +PREHOOK: query: -- testing skew on other data types - int +CREATE TABLE T1(key INT, val STRING) SKEWED BY (key) ON ((2)) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T1 +POSTHOOK: query: -- testing skew on other data types - int +CREATE TABLE T1(key INT, val STRING) SKEWED BY (key) ON ((2)) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T1 +PREHOOK: query: INSERT OVERWRITE TABLE T1 SELECT key, val FROM tmpT1 +PREHOOK: type: QUERY +PREHOOK: Input: default@tmpt1 +PREHOOK: Output: default@t1 +[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to +POSTHOOK: query: INSERT OVERWRITE TABLE T1 SELECT key, val FROM tmpT1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@tmpt1 +POSTHOOK: Output: default@t1 +POSTHOOK: Lineage: t1.key EXPRESSION [(tmpt1)tmpt1.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: t1.val SIMPLE [(tmpt1)tmpt1.FieldSchema(name:val, type:string, comment:null), ] +PREHOOK: query: CREATE TABLE tmpT2(key STRING, val STRING) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@tmpT2 +POSTHOOK: query: CREATE TABLE tmpT2(key STRING, val STRING) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@tmpT2 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE tmpT2 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@tmpt2 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE tmpT2 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@tmpt2 +PREHOOK: query: CREATE TABLE T2(key INT, val STRING) SKEWED BY (key) ON ((3)) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T2 +POSTHOOK: query: CREATE TABLE T2(key INT, val STRING) SKEWED BY (key) ON ((3)) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T2 +PREHOOK: query: INSERT OVERWRITE TABLE T2 SELECT key, val FROM tmpT2 +PREHOOK: type: QUERY +PREHOOK: Input: default@tmpt2 +PREHOOK: Output: default@t2 +[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to +POSTHOOK: query: INSERT OVERWRITE TABLE T2 SELECT key, val FROM tmpT2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@tmpt2 +POSTHOOK: Output: default@t2 +POSTHOOK: Lineage: t2.key EXPRESSION [(tmpt2)tmpt2.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: t2.val SIMPLE [(tmpt2)tmpt2.FieldSchema(name:val, type:string, comment:null), ] +PREHOOK: query: -- The skewed key is a integer column. +-- Otherwise this test is similar to skewjoinopt1.q +-- Both the joined tables are skewed, and the joined column +-- is an integer +-- adding a order by at the end to make the results deterministic + +EXPLAIN +SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key +PREHOOK: type: QUERY +POSTHOOK: query: -- The skewed key is a integer column. +-- Otherwise this test is similar to skewjoinopt1.q +-- Both the joined tables are skewed, and the joined column +-- is an integer +-- adding a order by at the end to make the results deterministic + +EXPLAIN +SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 3 (GROUP PARTITION-LEVEL SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + 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 + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions: val (type: string) + Map 3 + Map Operator Tree: + TableScan + alias: a + 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 + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions: val (type: string) + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col0, _col1, _col5, _col6 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + 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-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key +ORDER BY a.key, b.key, a.val, b.val +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +PREHOOK: Input: default@t2 +#### A masked pattern was here #### +POSTHOOK: query: SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key +ORDER BY a.key, b.key, a.val, b.val +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +POSTHOOK: Input: default@t2 +#### A masked pattern was here #### +2 12 2 22 +3 13 3 13 +8 18 8 18 +8 18 8 18 +8 28 8 18 +8 28 8 18 +PREHOOK: query: -- test outer joins also + +EXPLAIN +SELECT a.*, b.* FROM T1 a RIGHT OUTER JOIN T2 b ON a.key = b.key +PREHOOK: type: QUERY +POSTHOOK: query: -- test outer joins also + +EXPLAIN +SELECT a.*, b.* FROM T1 a RIGHT OUTER JOIN T2 b ON a.key = b.key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 3 (GROUP PARTITION-LEVEL SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE + value expressions: val (type: string) + Map 3 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE + value expressions: val (type: string) + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Right Outer Join0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col0, _col1, _col5, _col6 + Statistics: Num rows: 0 Data size: 33 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 0 Data size: 33 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 33 Basic stats: PARTIAL 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-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT a.*, b.* FROM T1 a RIGHT OUTER JOIN T2 b ON a.key = b.key +ORDER BY a.key, b.key, a.val, b.val +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +PREHOOK: Input: default@t2 +#### A masked pattern was here #### +POSTHOOK: query: SELECT a.*, b.* FROM T1 a RIGHT OUTER JOIN T2 b ON a.key = b.key +ORDER BY a.key, b.key, a.val, b.val +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +POSTHOOK: Input: default@t2 +#### A masked pattern was here #### +NULL NULL 4 14 +NULL NULL 5 15 +2 12 2 22 +3 13 3 13 +8 18 8 18 +8 18 8 18 +8 28 8 18 +8 28 8 18 +PREHOOK: query: -- an aggregation at the end should not change anything + +EXPLAIN +SELECT count(1) FROM T1 a JOIN T2 b ON a.key = b.key +PREHOOK: type: QUERY +POSTHOOK: query: -- an aggregation at the end should not change anything + +EXPLAIN +SELECT count(1) FROM T1 a JOIN T2 b ON a.key = b.key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 4 (GROUP PARTITION-LEVEL SORT, 1) + Reducer 3 <- Reducer 2 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 4 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 4 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Map 4 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 4 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 4 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 + 1 + Statistics: Num rows: 4 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Select Operator + Statistics: Num rows: 4 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(1) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Reducer 3 + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE 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-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT count(1) FROM T1 a JOIN T2 b ON a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +PREHOOK: Input: default@t2 +#### A masked pattern was here #### +POSTHOOK: query: SELECT count(1) FROM T1 a JOIN T2 b ON a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +POSTHOOK: Input: default@t2 +#### A masked pattern was here #### +6 +PREHOOK: query: EXPLAIN +SELECT count(1) FROM T1 a RIGHT OUTER JOIN T2 b ON a.key = b.key +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN +SELECT count(1) FROM T1 a RIGHT OUTER JOIN T2 b ON a.key = b.key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 4 (GROUP PARTITION-LEVEL SORT, 1) + Reducer 3 <- Reducer 2 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Map 4 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Right Outer Join0 to 1 + condition expressions: + 0 + 1 + Statistics: Num rows: 7 Data size: 33 Basic stats: COMPLETE Column stats: NONE + Select Operator + Statistics: Num rows: 7 Data size: 33 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(1) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Reducer 3 + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE 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-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT count(1) FROM T1 a RIGHT OUTER JOIN T2 b ON a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +PREHOOK: Input: default@t2 +#### A masked pattern was here #### +POSTHOOK: query: SELECT count(1) FROM T1 a RIGHT OUTER JOIN T2 b ON a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +POSTHOOK: Input: default@t2 +#### A masked pattern was here #### +8 Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt16.q.out URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt16.q.out?rev=1634671&view=auto ============================================================================== --- hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt16.q.out (added) +++ hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt16.q.out Mon Oct 27 19:56:58 2014 @@ -0,0 +1,130 @@ +PREHOOK: query: CREATE TABLE T1(key STRING, val STRING) +SKEWED BY (key, val) ON ((2, 12)) 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, val) ON ((2, 12)) 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) +SKEWED BY (key) ON ((3)) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T2 +POSTHOOK: query: CREATE TABLE T2(key STRING, val STRING) +SKEWED BY (key) ON ((3)) 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: -- One of the tables is skewed by 2 columns, and the other table is +-- skewed by one column. Ths join is performed on the both the columns +-- adding a order by at the end to make the results deterministic + +EXPLAIN +SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key and a.val = b.val +PREHOOK: type: QUERY +POSTHOOK: query: -- One of the tables is skewed by 2 columns, and the other table is +-- skewed by one column. Ths join is performed on the both the columns +-- adding a order by at the end to make the results deterministic + +EXPLAIN +SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key and a.val = b.val +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 3 (GROUP PARTITION-LEVEL SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + 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 val is not null) (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string), val (type: string) + sort order: ++ + Map-reduce partition columns: key (type: string), val (type: string) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Map 3 + Map Operator Tree: + 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 + Reduce Output Operator + key expressions: key (type: string), val (type: string) + sort order: ++ + Map-reduce partition columns: key (type: string), val (type: string) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {KEY.reducesinkkey1} + 1 {KEY.reducesinkkey0} {KEY.reducesinkkey1} + outputColumnNames: _col0, _col1, _col5, _col6 + 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) + outputColumnNames: _col0, _col1, _col2, _col3 + 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-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key and a.val = b.val +ORDER BY a.key, b.key, a.val, b.val +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +PREHOOK: Input: default@t2 +#### A masked pattern was here #### +POSTHOOK: query: SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key and a.val = b.val +ORDER BY a.key, b.key, a.val, b.val +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +POSTHOOK: Input: default@t2 +#### A masked pattern was here #### +3 13 3 13 +8 18 8 18 +8 18 8 18 Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt17.q.out URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt17.q.out?rev=1634671&view=auto ============================================================================== --- hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt17.q.out (added) +++ hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt17.q.out Mon Oct 27 19:56:58 2014 @@ -0,0 +1,285 @@ +PREHOOK: query: CREATE TABLE T1(key STRING, val STRING) +SKEWED BY (key, val) ON ((2, 12)) 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, val) ON ((2, 12)) 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) +SKEWED BY (key) ON ((2)) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T2 +POSTHOOK: query: CREATE TABLE T2(key STRING, val STRING) +SKEWED BY (key) ON ((2)) 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: -- One of the tables is skewed by 2 columns, and the other table is +-- skewed by one column. Ths join is performed on the first skewed column +-- The skewed value for the jon key is common to both the tables. +-- In this case, the skewed join value is not repeated in the filter. +-- adding a order by at the end to make the results deterministic + +EXPLAIN +SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key +PREHOOK: type: QUERY +POSTHOOK: query: -- One of the tables is skewed by 2 columns, and the other table is +-- skewed by one column. Ths join is performed on the first skewed column +-- The skewed value for the jon key is common to both the tables. +-- In this case, the skewed join value is not repeated in the filter. +-- adding a order by at the end to make the results deterministic + +EXPLAIN +SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 3 (GROUP PARTITION-LEVEL SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + 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 + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions: val (type: string) + Map 3 + Map Operator Tree: + TableScan + alias: a + 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 + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions: val (type: string) + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col0, _col1, _col5, _col6 + 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) + outputColumnNames: _col0, _col1, _col2, _col3 + 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-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key +ORDER BY a.key, b.key, a.val, b.val +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +PREHOOK: Input: default@t2 +#### A masked pattern was here #### +POSTHOOK: query: SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key +ORDER BY a.key, b.key, a.val, b.val +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +POSTHOOK: Input: default@t2 +#### A masked pattern was here #### +2 12 2 22 +3 13 3 13 +8 18 8 18 +8 18 8 18 +8 28 8 18 +8 28 8 18 +PREHOOK: query: DROP TABLE T1 +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@t1 +PREHOOK: Output: default@t1 +POSTHOOK: query: DROP TABLE T1 +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@t1 +POSTHOOK: Output: default@t1 +PREHOOK: query: DROP TABLE T2 +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@t2 +PREHOOK: Output: default@t2 +POSTHOOK: query: DROP TABLE T2 +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@t2 +POSTHOOK: Output: default@t2 +PREHOOK: query: CREATE TABLE T1(key STRING, val STRING) +SKEWED BY (key, val) ON ((2, 12)) 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, val) ON ((2, 12)) 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) +SKEWED BY (key) ON ((2)) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T2 +POSTHOOK: query: CREATE TABLE T2(key STRING, val STRING) +SKEWED BY (key) ON ((2)) 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: -- One of the tables is skewed by 2 columns, and the other table is +-- skewed by one column. Ths join is performed on the both the columns +-- In this case, the skewed join value is repeated in the filter. + +EXPLAIN +SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key and a.val = b.val +PREHOOK: type: QUERY +POSTHOOK: query: -- One of the tables is skewed by 2 columns, and the other table is +-- skewed by one column. Ths join is performed on the both the columns +-- In this case, the skewed join value is repeated in the filter. + +EXPLAIN +SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key and a.val = b.val +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 3 (GROUP PARTITION-LEVEL SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + 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 val is not null) (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string), val (type: string) + sort order: ++ + Map-reduce partition columns: key (type: string), val (type: string) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Map 3 + Map Operator Tree: + 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 + Reduce Output Operator + key expressions: key (type: string), val (type: string) + sort order: ++ + Map-reduce partition columns: key (type: string), val (type: string) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {KEY.reducesinkkey1} + 1 {KEY.reducesinkkey0} {KEY.reducesinkkey1} + outputColumnNames: _col0, _col1, _col5, _col6 + 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) + outputColumnNames: _col0, _col1, _col2, _col3 + 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-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key and a.val = b.val +ORDER BY a.key, b.key, a.val, b.val +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +PREHOOK: Input: default@t2 +#### A masked pattern was here #### +POSTHOOK: query: SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key and a.val = b.val +ORDER BY a.key, b.key, a.val, b.val +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +POSTHOOK: Input: default@t2 +#### A masked pattern was here #### +3 13 3 13 +8 18 8 18 +8 18 8 18 Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt18.q.out URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt18.q.out?rev=1634671&view=auto ============================================================================== --- hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt18.q.out (added) +++ hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt18.q.out Mon Oct 27 19:56:58 2014 @@ -0,0 +1,162 @@ +PREHOOK: query: CREATE TABLE tmpT1(key STRING, val STRING) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@tmpT1 +POSTHOOK: query: CREATE TABLE tmpT1(key STRING, val STRING) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@tmpT1 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE tmpT1 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@tmpt1 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE tmpT1 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@tmpt1 +PREHOOK: query: -- testing skew on other data types - int +CREATE TABLE T1(key INT, val STRING) SKEWED BY (key) ON ((2)) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T1 +POSTHOOK: query: -- testing skew on other data types - int +CREATE TABLE T1(key INT, val STRING) SKEWED BY (key) ON ((2)) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T1 +PREHOOK: query: INSERT OVERWRITE TABLE T1 SELECT key, val FROM tmpT1 +PREHOOK: type: QUERY +PREHOOK: Input: default@tmpt1 +PREHOOK: Output: default@t1 +[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to +POSTHOOK: query: INSERT OVERWRITE TABLE T1 SELECT key, val FROM tmpT1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@tmpt1 +POSTHOOK: Output: default@t1 +POSTHOOK: Lineage: t1.key EXPRESSION [(tmpt1)tmpt1.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: t1.val SIMPLE [(tmpt1)tmpt1.FieldSchema(name:val, type:string, comment:null), ] +PREHOOK: query: -- Tke skewed column is same in both the tables, however it is +-- INT in one of the tables, and STRING in the other table + +CREATE TABLE T2(key STRING, val STRING) +SKEWED BY (key) ON ((3)) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T2 +POSTHOOK: query: -- Tke skewed column is same in both the tables, however it is +-- INT in one of the tables, and STRING in the other table + +CREATE TABLE T2(key STRING, val STRING) +SKEWED BY (key) ON ((3)) 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: -- Once HIVE-3445 is fixed, the compile time skew join optimization would be +-- applicable here. Till the above jira is fixed, it would be performed as a +-- regular join +-- adding a order by at the end to make the results deterministic + +EXPLAIN +SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key +PREHOOK: type: QUERY +POSTHOOK: query: -- Once HIVE-3445 is fixed, the compile time skew join optimization would be +-- applicable here. Till the above jira is fixed, it would be performed as a +-- regular join +-- adding a order by at the end to make the results deterministic + +EXPLAIN +SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 3 (GROUP PARTITION-LEVEL SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: UDFToDouble(key) is not null (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reduce Output Operator + key expressions: UDFToDouble(key) (type: double) + sort order: + + Map-reduce partition columns: UDFToDouble(key) (type: double) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions: key (type: string), val (type: string) + Map 3 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: UDFToDouble(key) is not null (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reduce Output Operator + key expressions: UDFToDouble(key) (type: double) + sort order: + + Map-reduce partition columns: UDFToDouble(key) (type: double) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions: key (type: int), val (type: string) + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {VALUE._col0} {VALUE._col1} + 1 {VALUE._col0} {VALUE._col1} + outputColumnNames: _col0, _col1, _col5, _col6 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col5 (type: string), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + 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-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key +ORDER BY a.key, b.key, a.val, b.val +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +PREHOOK: Input: default@t2 +#### A masked pattern was here #### +POSTHOOK: query: SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key +ORDER BY a.key, b.key, a.val, b.val +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +POSTHOOK: Input: default@t2 +#### A masked pattern was here #### +2 12 2 22 +3 13 3 13 +8 18 8 18 +8 18 8 18 +8 28 8 18 +8 28 8 18 Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt19.q.out URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt19.q.out?rev=1634671&view=auto ============================================================================== --- hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt19.q.out (added) +++ hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt19.q.out Mon Oct 27 19:56:58 2014 @@ -0,0 +1,137 @@ +PREHOOK: query: CREATE TABLE T1(key STRING, val STRING) +CLUSTERED BY (key) INTO 4 BUCKETS +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) +CLUSTERED BY (key) INTO 4 BUCKETS +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: -- add a test where the skewed key is also the bucketized key +-- it should not matter, and the compile time skewed join +-- optimization is performed +-- adding a order by at the end to make the results deterministic + +EXPLAIN +SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key +PREHOOK: type: QUERY +POSTHOOK: query: -- add a test where the skewed key is also the bucketized key +-- it should not matter, and the compile time skewed join +-- optimization is performed +-- adding a order by at the end to make the results deterministic + +EXPLAIN +SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 3 (GROUP PARTITION-LEVEL SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + 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 + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions: val (type: string) + Map 3 + Map Operator Tree: + TableScan + alias: a + 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 + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions: val (type: string) + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col0, _col1, _col5, _col6 + 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) + outputColumnNames: _col0, _col1, _col2, _col3 + 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-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key +ORDER BY a.key, b.key, a.val, b.val +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +PREHOOK: Input: default@t2 +#### A masked pattern was here #### +POSTHOOK: query: SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key +ORDER BY a.key, b.key, a.val, b.val +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +POSTHOOK: Input: default@t2 +#### A masked pattern was here #### +2 12 2 22 +3 13 3 13 +8 18 8 18 +8 18 8 18 +8 28 8 18 +8 28 8 18 Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt20.q.out URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt20.q.out?rev=1634671&view=auto ============================================================================== --- hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt20.q.out (added) +++ hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt20.q.out Mon Oct 27 19:56:58 2014 @@ -0,0 +1,137 @@ +PREHOOK: query: CREATE TABLE T1(key STRING, val STRING) +CLUSTERED BY (key) SORTED BY (key) INTO 4 BUCKETS +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) +CLUSTERED BY (key) SORTED BY (key) INTO 4 BUCKETS +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: -- add a test where the skewed key is also the bucketized/sorted key +-- it should not matter, and the compile time skewed join +-- optimization is performed +-- adding a order by at the end to make the results deterministic + +EXPLAIN +SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key +PREHOOK: type: QUERY +POSTHOOK: query: -- add a test where the skewed key is also the bucketized/sorted key +-- it should not matter, and the compile time skewed join +-- optimization is performed +-- adding a order by at the end to make the results deterministic + +EXPLAIN +SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 3 (GROUP PARTITION-LEVEL SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + 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 + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions: val (type: string) + Map 3 + Map Operator Tree: + TableScan + alias: a + 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 + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions: val (type: string) + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col0, _col1, _col5, _col6 + 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) + outputColumnNames: _col0, _col1, _col2, _col3 + 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-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key +ORDER BY a.key, b.key, a.val, b.val +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +PREHOOK: Input: default@t2 +#### A masked pattern was here #### +POSTHOOK: query: SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key +ORDER BY a.key, b.key, a.val, b.val +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +POSTHOOK: Input: default@t2 +#### A masked pattern was here #### +2 12 2 22 +3 13 3 13 +8 18 8 18 +8 18 8 18 +8 28 8 18 +8 28 8 18 Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt3.q.out URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt3.q.out?rev=1634671&view=auto ============================================================================== --- hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt3.q.out (added) +++ hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt3.q.out Mon Oct 27 19:56:58 2014 @@ -0,0 +1,230 @@ +PREHOOK: query: CREATE TABLE T1(key STRING, val STRING) +SKEWED BY (key) ON ((2), (8)) 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), (8)) 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) +SKEWED BY (key) ON ((3), (8)) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T2 +POSTHOOK: query: CREATE TABLE T2(key STRING, val STRING) +SKEWED BY (key) ON ((3), (8)) 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: -- a simple query with skew on both the tables. One of the skewed +-- value is common to both the tables. The skewed value should not be +-- repeated in the filter. +-- adding a order by at the end to make the results deterministic + +EXPLAIN +SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key +PREHOOK: type: QUERY +POSTHOOK: query: -- a simple query with skew on both the tables. One of the skewed +-- value is common to both the tables. The skewed value should not be +-- repeated in the filter. +-- adding a order by at the end to make the results deterministic + +EXPLAIN +SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 3 (GROUP PARTITION-LEVEL SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + 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 + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions: val (type: string) + Map 3 + Map Operator Tree: + TableScan + alias: a + 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 + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions: val (type: string) + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col0, _col1, _col5, _col6 + 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) + outputColumnNames: _col0, _col1, _col2, _col3 + 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-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key +ORDER BY a.key, b.key, a.val, b.val +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +PREHOOK: Input: default@t2 +#### A masked pattern was here #### +POSTHOOK: query: SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key +ORDER BY a.key, b.key, a.val, b.val +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +POSTHOOK: Input: default@t2 +#### A masked pattern was here #### +2 12 2 22 +3 13 3 13 +8 18 8 18 +8 18 8 18 +8 28 8 18 +8 28 8 18 +PREHOOK: query: -- test outer joins also + +EXPLAIN +SELECT a.*, b.* FROM T1 a FULL OUTER JOIN T2 b ON a.key = b.key +PREHOOK: type: QUERY +POSTHOOK: query: -- test outer joins also + +EXPLAIN +SELECT a.*, b.* FROM T1 a FULL OUTER JOIN T2 b ON a.key = b.key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 3 (GROUP PARTITION-LEVEL SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE + value expressions: val (type: string) + Map 3 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE + value expressions: val (type: string) + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Outer Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col0, _col1, _col5, _col6 + Statistics: Num rows: 0 Data size: 33 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 0 Data size: 33 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 33 Basic stats: PARTIAL 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-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT a.*, b.* FROM T1 a FULL OUTER JOIN T2 b ON a.key = b.key +ORDER BY a.key, b.key, a.val, b.val +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +PREHOOK: Input: default@t2 +#### A masked pattern was here #### +POSTHOOK: query: SELECT a.*, b.* FROM T1 a FULL OUTER JOIN T2 b ON a.key = b.key +ORDER BY a.key, b.key, a.val, b.val +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +POSTHOOK: Input: default@t2 +#### A masked pattern was here #### +NULL NULL 4 14 +NULL NULL 5 15 +1 11 NULL NULL +2 12 2 22 +3 13 3 13 +7 17 NULL NULL +8 18 8 18 +8 18 8 18 +8 28 8 18 +8 28 8 18
