diff --git a/itests/src/test/resources/testconfiguration.properties b/itests/src/test/resources/testconfiguration.properties index 96d3029..598d682 100644 --- a/itests/src/test/resources/testconfiguration.properties +++ b/itests/src/test/resources/testconfiguration.properties @@ -309,13 +309,15 @@ minitez.query.files.shared=alter_merge_2_orc.q,\ auto_sortmerge_join_3.q,\ auto_sortmerge_join_4.q,\ auto_sortmerge_join_5.q,\ + auto_sortmerge_join_6.q,\ auto_sortmerge_join_7.q,\ auto_sortmerge_join_8.q,\ auto_sortmerge_join_9.q,\ auto_join30.q,\ auto_join21.q,\ auto_join29.q,\ - auto_join_filters.q + auto_join_filters.q,\ + auto_join_nulls.q minitez.query.files=bucket_map_join_tez1.q,\ diff --git a/ql/src/test/queries/clientpositive/auto_sortmerge_join_6.q b/ql/src/test/queries/clientpositive/auto_sortmerge_join_6.q index 309987b..0ddf378 100644 --- a/ql/src/test/queries/clientpositive/auto_sortmerge_join_6.q +++ b/ql/src/test/queries/clientpositive/auto_sortmerge_join_6.q @@ -1,6 +1,7 @@ set hive.enforce.bucketing = true; set hive.enforce.sorting = true; set hive.exec.reducers.max = 1; +set hive.explain.user=false; CREATE TABLE tbl1(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS; CREATE TABLE tbl2(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS; diff --git a/ql/src/test/results/clientpositive/llap/auto_join_nulls.q.out b/ql/src/test/results/clientpositive/llap/auto_join_nulls.q.out new file mode 100644 index 0000000..b9a759f --- /dev/null +++ b/ql/src/test/results/clientpositive/llap/auto_join_nulls.q.out @@ -0,0 +1,217 @@ +PREHOOK: query: CREATE TABLE myinput1(key int, value int) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@myinput1 +POSTHOOK: query: CREATE TABLE myinput1(key int, value int) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@myinput1 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/in1.txt' INTO TABLE myinput1 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@myinput1 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/in1.txt' INTO TABLE myinput1 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@myinput1 +Warning: Map Join MAPJOIN[16][bigTable=?] in task 'Map 1' is a cross product +PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a JOIN myinput1 b +PREHOOK: type: QUERY +PREHOOK: Input: default@myinput1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a JOIN myinput1 b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@myinput1 +#### A masked pattern was here #### +13630578 +Warning: Map Join MAPJOIN[15][bigTable=?] in task 'Map 1' is a cross product +PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a LEFT OUTER JOIN myinput1 b +PREHOOK: type: QUERY +PREHOOK: Input: default@myinput1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a LEFT OUTER JOIN myinput1 b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@myinput1 +#### A masked pattern was here #### +13630578 +Warning: Map Join MAPJOIN[15][bigTable=?] in task 'Map 1' is a cross product +PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a RIGHT OUTER JOIN myinput1 b +PREHOOK: type: QUERY +PREHOOK: Input: default@myinput1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a RIGHT OUTER JOIN myinput1 b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@myinput1 +#### A masked pattern was here #### +13630578 +PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a JOIN myinput1 b ON a.key = b.value +PREHOOK: type: QUERY +PREHOOK: Input: default@myinput1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a JOIN myinput1 b ON a.key = b.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@myinput1 +#### A masked pattern was here #### +3078400 +PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a JOIN myinput1 b ON a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@myinput1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a JOIN myinput1 b ON a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@myinput1 +#### A masked pattern was here #### +4509856 +PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a JOIN myinput1 b ON a.value = b.value +PREHOOK: type: QUERY +PREHOOK: Input: default@myinput1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a JOIN myinput1 b ON a.value = b.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@myinput1 +#### A masked pattern was here #### +3112070 +PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a JOIN myinput1 b ON a.value = b.value and a.key=b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@myinput1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a JOIN myinput1 b ON a.value = b.value and a.key=b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@myinput1 +#### A masked pattern was here #### +3078400 +PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a LEFT OUTER JOIN myinput1 b ON a.key = b.value +PREHOOK: type: QUERY +PREHOOK: Input: default@myinput1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a LEFT OUTER JOIN myinput1 b ON a.key = b.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@myinput1 +#### A masked pattern was here #### +4542003 +PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a LEFT OUTER JOIN myinput1 b ON a.value = b.value +PREHOOK: type: QUERY +PREHOOK: Input: default@myinput1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a LEFT OUTER JOIN myinput1 b ON a.value = b.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@myinput1 +#### A masked pattern was here #### +4542038 +PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a LEFT OUTER JOIN myinput1 b ON a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@myinput1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a LEFT OUTER JOIN myinput1 b ON a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@myinput1 +#### A masked pattern was here #### +4543491 +PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a LEFT OUTER JOIN myinput1 b ON a.key = b.key and a.value=b.value +PREHOOK: type: QUERY +PREHOOK: Input: default@myinput1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a LEFT OUTER JOIN myinput1 b ON a.key = b.key and a.value=b.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@myinput1 +#### A masked pattern was here #### +4542003 +PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a RIGHT OUTER JOIN myinput1 b ON a.key = b.value +PREHOOK: type: QUERY +PREHOOK: Input: default@myinput1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a RIGHT OUTER JOIN myinput1 b ON a.key = b.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@myinput1 +#### A masked pattern was here #### +3079923 +PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a RIGHT OUTER JOIN myinput1 b ON a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@myinput1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a RIGHT OUTER JOIN myinput1 b ON a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@myinput1 +#### A masked pattern was here #### +4509891 +PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a RIGHT OUTER JOIN myinput1 b ON a.value = b.value +PREHOOK: type: QUERY +PREHOOK: Input: default@myinput1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a RIGHT OUTER JOIN myinput1 b ON a.value = b.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@myinput1 +#### A masked pattern was here #### +3113558 +PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a RIGHT OUTER JOIN myinput1 b ON a.key=b.key and a.value = b.value +PREHOOK: type: QUERY +PREHOOK: Input: default@myinput1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a RIGHT OUTER JOIN myinput1 b ON a.key=b.key and a.value = b.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@myinput1 +#### A masked pattern was here #### +3079923 +PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a FULL OUTER JOIN myinput1 b ON a.key = b.value +PREHOOK: type: QUERY +PREHOOK: Input: default@myinput1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a FULL OUTER JOIN myinput1 b ON a.key = b.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@myinput1 +#### A masked pattern was here #### +4543526 +PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a FULL OUTER JOIN myinput1 b ON a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@myinput1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a FULL OUTER JOIN myinput1 b ON a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@myinput1 +#### A masked pattern was here #### +4543526 +PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a FULL OUTER JOIN myinput1 b ON a.value = b.value +PREHOOK: type: QUERY +PREHOOK: Input: default@myinput1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a FULL OUTER JOIN myinput1 b ON a.value = b.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@myinput1 +#### A masked pattern was here #### +4543526 +PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a FULL OUTER JOIN myinput1 b ON a.value = b.value and a.key=b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@myinput1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a FULL OUTER JOIN myinput1 b ON a.value = b.value and a.key=b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@myinput1 +#### A masked pattern was here #### +4543526 +PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) from myinput1 a LEFT OUTER JOIN myinput1 b ON (a.value=b.value) RIGHT OUTER JOIN myinput1 c ON (b.value=c.value) +PREHOOK: type: QUERY +PREHOOK: Input: default@myinput1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) from myinput1 a LEFT OUTER JOIN myinput1 b ON (a.value=b.value) RIGHT OUTER JOIN myinput1 c ON (b.value=c.value) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@myinput1 +#### A masked pattern was here #### +3112070 +PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) from myinput1 a RIGHT OUTER JOIN myinput1 b ON (a.value=b.value) LEFT OUTER JOIN myinput1 c ON (b.value=c.value) +PREHOOK: type: QUERY +PREHOOK: Input: default@myinput1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) from myinput1 a RIGHT OUTER JOIN myinput1 b ON (a.value=b.value) LEFT OUTER JOIN myinput1 c ON (b.value=c.value) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@myinput1 +#### A masked pattern was here #### +3113558 +PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a LEFT OUTER JOIN myinput1 b RIGHT OUTER JOIN myinput1 c ON a.value = b.value and b.value = c.value +PREHOOK: type: QUERY +PREHOOK: Input: default@myinput1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a LEFT OUTER JOIN myinput1 b RIGHT OUTER JOIN myinput1 c ON a.value = b.value and b.value = c.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@myinput1 +#### A masked pattern was here #### +3112070 diff --git a/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_6.q.out b/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_6.q.out new file mode 100644 index 0000000..16a6f43 --- /dev/null +++ b/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_6.q.out @@ -0,0 +1,1200 @@ +PREHOOK: query: CREATE TABLE tbl1(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@tbl1 +POSTHOOK: query: CREATE TABLE tbl1(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@tbl1 +PREHOOK: query: CREATE TABLE tbl2(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@tbl2 +POSTHOOK: query: CREATE TABLE tbl2(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@tbl2 +PREHOOK: query: CREATE TABLE tbl3(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@tbl3 +POSTHOOK: query: CREATE TABLE tbl3(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@tbl3 +PREHOOK: query: CREATE TABLE tbl4(key int, value string) CLUSTERED BY (value) SORTED BY (value) INTO 2 BUCKETS +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@tbl4 +POSTHOOK: query: CREATE TABLE tbl4(key int, value string) CLUSTERED BY (value) SORTED BY (value) INTO 2 BUCKETS +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@tbl4 +PREHOOK: query: insert overwrite table tbl1 select * from src +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@tbl1 +POSTHOOK: query: insert overwrite table tbl1 select * from src +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@tbl1 +POSTHOOK: Lineage: tbl1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: tbl1.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: insert overwrite table tbl2 select * from src +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@tbl2 +POSTHOOK: query: insert overwrite table tbl2 select * from src +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@tbl2 +POSTHOOK: Lineage: tbl2.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: tbl2.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: insert overwrite table tbl3 select * from src +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@tbl3 +POSTHOOK: query: insert overwrite table tbl3 select * from src +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@tbl3 +POSTHOOK: Lineage: tbl3.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: tbl3.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: insert overwrite table tbl4 select * from src +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@tbl4 +POSTHOOK: query: insert overwrite table tbl4 select * from src +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@tbl4 +POSTHOOK: Lineage: tbl4.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: tbl4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: -- A SMB join is being followed by a regular join on a non-bucketed table on a different key + +-- Three tests below are all the same query with different alias, which changes dispatch order of GenMapRedWalker +-- This is dependent to iteration order of HashMap, so can be meaningless in non-sun jdk +-- b = TS[0]-OP[13]-MAPJOIN[11]-RS[6]-JOIN[8]-SEL[9]-FS[10] +-- c = TS[1]-RS[7]-JOIN[8] +-- a = TS[2]-MAPJOIN[11] +explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src c on c.value = a.value +PREHOOK: type: QUERY +POSTHOOK: query: -- A SMB join is being followed by a regular join on a non-bucketed table on a different key + +-- Three tests below are all the same query with different alias, which changes dispatch order of GenMapRedWalker +-- This is dependent to iteration order of HashMap, so can be meaningless in non-sun jdk +-- b = TS[0]-OP[13]-MAPJOIN[11]-RS[6]-JOIN[8]-SEL[9]-FS[10] +-- c = TS[1]-RS[7]-JOIN[8] +-- a = TS[2]-MAPJOIN[11] +explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src c on c.value = a.value +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: int) + 1 key (type: int) + outputColumnNames: _col1 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Execution mode: llap + Map 5 + Map Operator Tree: + TableScan + alias: c + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: value is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: value (type: string) + sort order: + + Map-reduce partition columns: value (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Execution mode: llap + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 value (type: string) + Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + 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 + Execution mode: uber + 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 + 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(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src c on c.value = a.value +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@tbl1 +PREHOOK: Input: default@tbl2 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src c on c.value = a.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@tbl1 +POSTHOOK: Input: default@tbl2 +#### A masked pattern was here #### +2654 +PREHOOK: query: -- d = TS[0]-RS[7]-JOIN[8]-SEL[9]-FS[10] +-- b = TS[1]-OP[13]-MAPJOIN[11]-RS[6]-JOIN[8] +-- a = TS[2]-MAPJOIN[11] +explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src d on d.value = a.value +PREHOOK: type: QUERY +POSTHOOK: query: -- d = TS[0]-RS[7]-JOIN[8]-SEL[9]-FS[10] +-- b = TS[1]-OP[13]-MAPJOIN[11]-RS[6]-JOIN[8] +-- a = TS[2]-MAPJOIN[11] +explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src d on d.value = a.value +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: int) + 1 key (type: int) + outputColumnNames: _col1 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Execution mode: llap + Map 5 + Map Operator Tree: + TableScan + alias: d + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: value is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: value (type: string) + sort order: + + Map-reduce partition columns: value (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Execution mode: llap + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 value (type: string) + Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + 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 + Execution mode: uber + 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 + 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(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src d on d.value = a.value +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@tbl1 +PREHOOK: Input: default@tbl2 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src d on d.value = a.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@tbl1 +POSTHOOK: Input: default@tbl2 +#### A masked pattern was here #### +2654 +PREHOOK: query: -- b = TS[0]-OP[13]-MAPJOIN[11]-RS[6]-JOIN[8]-SEL[9]-FS[10] +-- a = TS[1]-MAPJOIN[11] +-- h = TS[2]-RS[7]-JOIN[8] +explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src h on h.value = a.value +PREHOOK: type: QUERY +POSTHOOK: query: -- b = TS[0]-OP[13]-MAPJOIN[11]-RS[6]-JOIN[8]-SEL[9]-FS[10] +-- a = TS[1]-MAPJOIN[11] +-- h = TS[2]-RS[7]-JOIN[8] +explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src h on h.value = a.value +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: int) + 1 key (type: int) + outputColumnNames: _col1 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Execution mode: llap + Map 5 + Map Operator Tree: + TableScan + alias: h + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: value is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: value (type: string) + sort order: + + Map-reduce partition columns: value (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Execution mode: llap + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 value (type: string) + Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + 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 + Execution mode: uber + 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 + 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(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src h on h.value = a.value +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@tbl1 +PREHOOK: Input: default@tbl2 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src h on h.value = a.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@tbl1 +POSTHOOK: Input: default@tbl2 +#### A masked pattern was here #### +2654 +PREHOOK: query: -- A SMB join is being followed by a regular join on a non-bucketed table on the same key +explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src c on c.key = a.key +PREHOOK: type: QUERY +POSTHOOK: query: -- A SMB join is being followed by a regular join on a non-bucketed table on the same key +explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src c on c.key = a.key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: UDFToDouble(key) is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Execution mode: llap + Map 4 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: UDFToDouble(key) is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Execution mode: llap + Map 5 + Map Operator Tree: + TableScan + alias: c + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: UDFToDouble(key) is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Execution mode: llap + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + Inner Join 0 to 2 + keys: + 0 UDFToDouble(key) (type: double) + 1 UDFToDouble(key) (type: double) + 2 UDFToDouble(key) (type: double) + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + 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 + Execution mode: uber + 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 + 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(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src c on c.key = a.key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@tbl1 +PREHOOK: Input: default@tbl2 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src c on c.key = a.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@tbl1 +POSTHOOK: Input: default@tbl2 +#### A masked pattern was here #### +2654 +PREHOOK: query: -- A SMB join is being followed by a regular join on a bucketed table on the same key +explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join tbl3 c on c.key = a.key +PREHOOK: type: QUERY +POSTHOOK: query: -- A SMB join is being followed by a regular join on a bucketed table on the same key +explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join tbl3 c on c.key = a.key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Operator Tree: + TableScan + alias: c + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator + condition map: + Inner Join 0 to 1 + Inner Join 0 to 2 + keys: + 0 key (type: int) + 1 key (type: int) + 2 key (type: int) + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + 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) + Execution mode: llap + Reducer 2 + Execution mode: uber + 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 + 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(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join tbl3 c on c.key = a.key +PREHOOK: type: QUERY +PREHOOK: Input: default@tbl1 +PREHOOK: Input: default@tbl2 +PREHOOK: Input: default@tbl3 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join tbl3 c on c.key = a.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@tbl1 +POSTHOOK: Input: default@tbl2 +POSTHOOK: Input: default@tbl3 +#### A masked pattern was here #### +2654 +PREHOOK: query: -- A SMB join is being followed by a regular join on a bucketed table on a different key +explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join tbl4 c on c.value = a.value +PREHOOK: type: QUERY +POSTHOOK: query: -- A SMB join is being followed by a regular join on a bucketed table on a different key +explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join tbl4 c on c.value = a.value +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: int) + 1 key (type: int) + outputColumnNames: _col1 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Execution mode: llap + Map 5 + Map Operator Tree: + TableScan + alias: c + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: value is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: value (type: string) + sort order: + + Map-reduce partition columns: value (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Execution mode: llap + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 value (type: string) + Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + 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 + Execution mode: uber + 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 + 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(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join tbl4 c on c.value = a.value +PREHOOK: type: QUERY +PREHOOK: Input: default@tbl1 +PREHOOK: Input: default@tbl2 +PREHOOK: Input: default@tbl4 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join tbl4 c on c.value = a.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@tbl1 +POSTHOOK: Input: default@tbl2 +POSTHOOK: Input: default@tbl4 +#### A masked pattern was here #### +2654 +PREHOOK: query: -- A SMB join is being followed by a regular join on a non-bucketed table on a different key +explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src c on c.value = a.value +PREHOOK: type: QUERY +POSTHOOK: query: -- A SMB join is being followed by a regular join on a non-bucketed table on a different key +explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src c on c.value = a.value +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: int) + 1 key (type: int) + outputColumnNames: _col1 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Execution mode: llap + Map 5 + Map Operator Tree: + TableScan + alias: c + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: value is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: value (type: string) + sort order: + + Map-reduce partition columns: value (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Execution mode: llap + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 value (type: string) + Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + 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 + Execution mode: uber + 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 + 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(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src c on c.value = a.value +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@tbl1 +PREHOOK: Input: default@tbl2 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src c on c.value = a.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@tbl1 +POSTHOOK: Input: default@tbl2 +#### A masked pattern was here #### +2654 +PREHOOK: query: -- A SMB join is being followed by a regular join on a non-bucketed table on the same key +explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src c on c.key = a.key +PREHOOK: type: QUERY +POSTHOOK: query: -- A SMB join is being followed by a regular join on a non-bucketed table on the same key +explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src c on c.key = a.key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: UDFToDouble(key) is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Execution mode: llap + Map 4 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: UDFToDouble(key) is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Execution mode: llap + Map 5 + Map Operator Tree: + TableScan + alias: c + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: UDFToDouble(key) is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Execution mode: llap + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + Inner Join 0 to 2 + keys: + 0 UDFToDouble(key) (type: double) + 1 UDFToDouble(key) (type: double) + 2 UDFToDouble(key) (type: double) + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + 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 + Execution mode: uber + 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 + 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(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src c on c.key = a.key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@tbl1 +PREHOOK: Input: default@tbl2 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src c on c.key = a.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@tbl1 +POSTHOOK: Input: default@tbl2 +#### A masked pattern was here #### +2654 +PREHOOK: query: -- A SMB join is being followed by a regular join on a bucketed table on the same key +explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join tbl3 c on c.key = a.key +PREHOOK: type: QUERY +POSTHOOK: query: -- A SMB join is being followed by a regular join on a bucketed table on the same key +explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join tbl3 c on c.key = a.key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Operator Tree: + TableScan + alias: c + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator + condition map: + Inner Join 0 to 1 + Inner Join 0 to 2 + keys: + 0 key (type: int) + 1 key (type: int) + 2 key (type: int) + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + 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) + Execution mode: llap + Reducer 2 + Execution mode: uber + 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 + 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(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join tbl3 c on c.key = a.key +PREHOOK: type: QUERY +PREHOOK: Input: default@tbl1 +PREHOOK: Input: default@tbl2 +PREHOOK: Input: default@tbl3 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join tbl3 c on c.key = a.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@tbl1 +POSTHOOK: Input: default@tbl2 +POSTHOOK: Input: default@tbl3 +#### A masked pattern was here #### +2654 +PREHOOK: query: -- A SMB join is being followed by a regular join on a bucketed table on a different key +explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join tbl4 c on c.value = a.value +PREHOOK: type: QUERY +POSTHOOK: query: -- A SMB join is being followed by a regular join on a bucketed table on a different key +explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join tbl4 c on c.value = a.value +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: int) + 1 key (type: int) + outputColumnNames: _col1 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Execution mode: llap + Map 5 + Map Operator Tree: + TableScan + alias: c + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: value is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: value (type: string) + sort order: + + Map-reduce partition columns: value (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Execution mode: llap + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 value (type: string) + Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + 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 + Execution mode: uber + 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 + 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(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join tbl4 c on c.value = a.value +PREHOOK: type: QUERY +PREHOOK: Input: default@tbl1 +PREHOOK: Input: default@tbl2 +PREHOOK: Input: default@tbl4 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join tbl4 c on c.value = a.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@tbl1 +POSTHOOK: Input: default@tbl2 +POSTHOOK: Input: default@tbl4 +#### A masked pattern was here #### +2654 diff --git a/ql/src/test/results/clientpositive/tez/auto_join_nulls.q.out b/ql/src/test/results/clientpositive/tez/auto_join_nulls.q.out index 20d71f4..b9a759f 100644 --- a/ql/src/test/results/clientpositive/tez/auto_join_nulls.q.out +++ b/ql/src/test/results/clientpositive/tez/auto_join_nulls.q.out @@ -34,7 +34,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@myinput1 #### A masked pattern was here #### 13630578 -Warning: Map Join MAPJOIN[16][bigTable=?] in task 'Map 1' is a cross product +Warning: Map Join MAPJOIN[15][bigTable=?] in task 'Map 1' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a RIGHT OUTER JOIN myinput1 b PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 diff --git a/ql/src/test/results/clientpositive/tez/auto_sortmerge_join_6.q.out b/ql/src/test/results/clientpositive/tez/auto_sortmerge_join_6.q.out index e6aec1a..9fc559d 100644 --- a/ql/src/test/results/clientpositive/tez/auto_sortmerge_join_6.q.out +++ b/ql/src/test/results/clientpositive/tez/auto_sortmerge_join_6.q.out @@ -166,17 +166,13 @@ STAGE PLANS: 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 + File Output Operator + compressed: false 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 + 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 @@ -285,17 +281,13 @@ STAGE PLANS: 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 + File Output Operator + compressed: false 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 + 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 @@ -404,17 +396,13 @@ STAGE PLANS: 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 + File Output Operator + compressed: false 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 + 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 @@ -519,17 +507,13 @@ STAGE PLANS: 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 + File Output Operator + compressed: false 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 + 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 @@ -614,17 +598,13 @@ STAGE PLANS: 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 + File Output Operator + compressed: false 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 + 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 @@ -729,17 +709,13 @@ STAGE PLANS: 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 + File Output Operator + compressed: false 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 + 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 @@ -844,17 +820,13 @@ STAGE PLANS: 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 + File Output Operator + compressed: false 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 + 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 @@ -959,17 +931,13 @@ STAGE PLANS: 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 + File Output Operator + compressed: false 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 + 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 @@ -1054,17 +1022,13 @@ STAGE PLANS: 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 + File Output Operator + compressed: false 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 + 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 @@ -1169,17 +1133,13 @@ STAGE PLANS: 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 + File Output Operator + compressed: false 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 + 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