http://git-wip-us.apache.org/repos/asf/hive/blob/42216997/ql/src/test/results/clientpositive/spark/spark_vectorized_dynamic_partition_pruning.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/spark_vectorized_dynamic_partition_pruning.q.out b/ql/src/test/results/clientpositive/spark/spark_vectorized_dynamic_partition_pruning.q.out new file mode 100644 index 0000000..9cab06c --- /dev/null +++ b/ql/src/test/results/clientpositive/spark/spark_vectorized_dynamic_partition_pruning.q.out @@ -0,0 +1,5822 @@ +PREHOOK: query: select distinct ds from srcpart +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: select distinct ds from srcpart +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +2008-04-08 +2008-04-09 +PREHOOK: query: select distinct hr from srcpart +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: select distinct hr from srcpart +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +11 +12 +PREHOOK: query: EXPLAIN create table srcpart_date as select ds as ds, ds as `date` from srcpart group by ds +PREHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: query: EXPLAIN create table srcpart_date as select ds as ds, ds as `date` from srcpart group by ds +POSTHOOK: type: CREATETABLE_AS_SELECT +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + Stage-3 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-3 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP, 2) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcpart + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1000 Data size: 10624 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 + name: default.srcpart_date + Execution mode: vectorized + + Stage: Stage-0 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + + Stage: Stage-3 + Create Table Operator: + Create Table + columns: ds string, date string + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat + serde name: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart_date + + Stage: Stage-2 + Stats-Aggr Operator + +PREHOOK: query: create table srcpart_date stored as orc as select ds as ds, ds as `date` from srcpart group by ds +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +PREHOOK: Output: database:default +PREHOOK: Output: default@srcpart_date +POSTHOOK: query: create table srcpart_date stored as orc as select ds as ds, ds as `date` from srcpart group by ds +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +POSTHOOK: Output: database:default +POSTHOOK: Output: default@srcpart_date +PREHOOK: query: create table srcpart_hour stored as orc as select hr as hr, hr as hour from srcpart group by hr +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +PREHOOK: Output: database:default +PREHOOK: Output: default@srcpart_hour +POSTHOOK: query: create table srcpart_hour stored as orc as select hr as hr, hr as hour from srcpart group by hr +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +POSTHOOK: Output: database:default +POSTHOOK: Output: default@srcpart_hour +PREHOOK: query: create table srcpart_date_hour stored as orc as select ds as ds, ds as `date`, hr as hr, hr as hour from srcpart group by ds, hr +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +PREHOOK: Output: database:default +PREHOOK: Output: default@srcpart_date_hour +POSTHOOK: query: create table srcpart_date_hour stored as orc as select ds as ds, ds as `date`, hr as hr, hr as hour from srcpart group by ds, hr +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +POSTHOOK: Output: database:default +POSTHOOK: Output: default@srcpart_date_hour +PREHOOK: query: create table srcpart_double_hour stored as orc as select (hr*2) as hr, hr as hour from srcpart group by hr +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +PREHOOK: Output: database:default +PREHOOK: Output: default@srcpart_double_hour +POSTHOOK: query: create table srcpart_double_hour stored as orc as select (hr*2) as hr, hr as hour from srcpart group by hr +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +POSTHOOK: Output: database:default +POSTHOOK: Output: default@srcpart_double_hour +PREHOOK: query: -- single column, single key +EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08' +PREHOOK: type: QUERY +POSTHOOK: query: -- single column, single key +EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08' +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-1 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Spark +#### A masked pattern was here #### + Vertices: + Map 5 + Map Operator Tree: + TableScan + alias: srcpart_date + filterExpr: (ds is not null and (date = '2008-04-08')) (type: boolean) + Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (ds is not null and (date = '2008-04-08')) (type: boolean) + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 1 + Execution mode: vectorized + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2) + Reducer 3 <- Reducer 2 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcpart + filterExpr: ds is not null (type: boolean) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: ds (type: string) + sort order: + + Map-reduce partition columns: ds (type: string) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Map 4 + Map Operator Tree: + TableScan + alias: srcpart_date + filterExpr: (ds is not null and (date = '2008-04-08')) (type: boolean) + Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (ds is not null and (date = '2008-04-08')) (type: boolean) + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: ds (type: string) + sort order: + + Map-reduce partition columns: ds (type: string) + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 ds (type: string) + 1 ds (type: string) + Statistics: Num rows: 2200 Data size: 23372 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 + 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 + Execution mode: vectorized + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08' +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +PREHOOK: Input: default@srcpart_date +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +POSTHOOK: Input: default@srcpart_date +#### A masked pattern was here #### +1000 +PREHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08' +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08' +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 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2) + Reducer 3 <- Reducer 2 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcpart + filterExpr: ds is not null (type: boolean) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: ds (type: string) + sort order: + + Map-reduce partition columns: ds (type: string) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Map 4 + Map Operator Tree: + TableScan + alias: srcpart_date + filterExpr: (ds is not null and (date = '2008-04-08')) (type: boolean) + Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (ds is not null and (date = '2008-04-08')) (type: boolean) + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: ds (type: string) + sort order: + + Map-reduce partition columns: ds (type: string) + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 ds (type: string) + 1 ds (type: string) + Statistics: Num rows: 2200 Data size: 23372 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 + 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 + Execution mode: vectorized + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08' +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +PREHOOK: Input: default@srcpart_date +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +POSTHOOK: Input: default@srcpart_date +#### A masked pattern was here #### +1000 +PREHOOK: query: select count(*) from srcpart where ds = '2008-04-08' +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from srcpart where ds = '2008-04-08' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +1000 +PREHOOK: query: -- multiple sources, single key +EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr) +where srcpart_date.`date` = '2008-04-08' and srcpart_hour.hour = 11 +PREHOOK: type: QUERY +POSTHOOK: query: -- multiple sources, single key +EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr) +where srcpart_date.`date` = '2008-04-08' and srcpart_hour.hour = 11 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-1 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Spark +#### A masked pattern was here #### + Vertices: + Map 7 + Map Operator Tree: + TableScan + alias: srcpart_date + filterExpr: (ds is not null and (date = '2008-04-08')) (type: boolean) + Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (ds is not null and (date = '2008-04-08')) (type: boolean) + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 1 + Execution mode: vectorized + Map 8 + Map Operator Tree: + TableScan + alias: srcpart_hour + filterExpr: (hr is not null and (hour = 11)) (type: boolean) + Statistics: Num rows: 2 Data size: 344 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (hr is not null and (hour = 11)) (type: boolean) + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Spark Partition Pruning Sink Operator + partition key expr: hr + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + target column name: hr + target work: Map 1 + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 5 (PARTITION-LEVEL SORT, 2) + Reducer 3 <- Map 6 (PARTITION-LEVEL SORT, 2), Reducer 2 (PARTITION-LEVEL SORT, 2) + Reducer 4 <- Reducer 3 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcpart + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: ds (type: string) + sort order: + + Map-reduce partition columns: ds (type: string) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + value expressions: hr (type: string) + Map 5 + Map Operator Tree: + TableScan + alias: srcpart_date + filterExpr: (ds is not null and (date = '2008-04-08')) (type: boolean) + Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (ds is not null and (date = '2008-04-08')) (type: boolean) + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: ds (type: string) + sort order: + + Map-reduce partition columns: ds (type: string) + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized + Map 6 + Map Operator Tree: + TableScan + alias: srcpart_hour + filterExpr: (hr is not null and (hour = 11)) (type: boolean) + Statistics: Num rows: 2 Data size: 344 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (hr is not null and (hour = 11)) (type: boolean) + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: hr (type: string) + sort order: + + Map-reduce partition columns: hr (type: string) + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 ds (type: string) + 1 ds (type: string) + outputColumnNames: _col3 + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col3 (type: string) + sort order: + + Map-reduce partition columns: _col3 (type: string) + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Reducer 3 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col3 (type: string) + 1 hr (type: string) + Statistics: Num rows: 2420 Data size: 25709 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 4 + 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 + Execution mode: vectorized + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr) +where srcpart_date.`date` = '2008-04-08' and srcpart_hour.hour = 11 +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +PREHOOK: Input: default@srcpart_date +PREHOOK: Input: default@srcpart_hour +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr) +where srcpart_date.`date` = '2008-04-08' and srcpart_hour.hour = 11 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +POSTHOOK: Input: default@srcpart_date +POSTHOOK: Input: default@srcpart_hour +#### A masked pattern was here #### +500 +PREHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr) +where srcpart_date.`date` = '2008-04-08' and srcpart_hour.hour = 11 +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr) +where srcpart_date.`date` = '2008-04-08' and srcpart_hour.hour = 11 +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 (PARTITION-LEVEL SORT, 2), Map 5 (PARTITION-LEVEL SORT, 2) + Reducer 3 <- Map 6 (PARTITION-LEVEL SORT, 2), Reducer 2 (PARTITION-LEVEL SORT, 2) + Reducer 4 <- Reducer 3 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcpart + filterExpr: (ds is not null and hr is not null) (type: boolean) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: ds (type: string) + sort order: + + Map-reduce partition columns: ds (type: string) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + value expressions: hr (type: string) + Map 5 + Map Operator Tree: + TableScan + alias: srcpart_date + filterExpr: (ds is not null and (date = '2008-04-08')) (type: boolean) + Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (ds is not null and (date = '2008-04-08')) (type: boolean) + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: ds (type: string) + sort order: + + Map-reduce partition columns: ds (type: string) + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized + Map 6 + Map Operator Tree: + TableScan + alias: srcpart_hour + filterExpr: (hr is not null and (hour = 11)) (type: boolean) + Statistics: Num rows: 2 Data size: 344 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (hr is not null and (hour = 11)) (type: boolean) + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: hr (type: string) + sort order: + + Map-reduce partition columns: hr (type: string) + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 ds (type: string) + 1 ds (type: string) + outputColumnNames: _col3 + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col3 (type: string) + sort order: + + Map-reduce partition columns: _col3 (type: string) + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Reducer 3 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col3 (type: string) + 1 hr (type: string) + Statistics: Num rows: 2420 Data size: 25709 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 4 + 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 + Execution mode: vectorized + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr) +where srcpart_date.`date` = '2008-04-08' and srcpart_hour.hour = 11 +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +PREHOOK: Input: default@srcpart_date +PREHOOK: Input: default@srcpart_hour +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr) +where srcpart_date.`date` = '2008-04-08' and srcpart_hour.hour = 11 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +POSTHOOK: Input: default@srcpart_date +POSTHOOK: Input: default@srcpart_hour +#### A masked pattern was here #### +500 +PREHOOK: query: select count(*) from srcpart where hr = 11 and ds = '2008-04-08' +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from srcpart where hr = 11 and ds = '2008-04-08' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +#### A masked pattern was here #### +500 +PREHOOK: query: -- multiple columns single source +EXPLAIN select count(*) from srcpart join srcpart_date_hour on (srcpart.ds = srcpart_date_hour.ds and srcpart.hr = srcpart_date_hour.hr) where srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11 +PREHOOK: type: QUERY +POSTHOOK: query: -- multiple columns single source +EXPLAIN select count(*) from srcpart join srcpart_date_hour on (srcpart.ds = srcpart_date_hour.ds and srcpart.hr = srcpart_date_hour.hr) where srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-1 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Spark +#### A masked pattern was here #### + Vertices: + Map 5 + Map Operator Tree: + TableScan + alias: srcpart_date_hour + filterExpr: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean) + Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean) + Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 1 + Map 6 + Map Operator Tree: + TableScan + alias: srcpart_date_hour + filterExpr: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean) + Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean) + Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Spark Partition Pruning Sink Operator + partition key expr: hr + Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + target column name: hr + target work: Map 1 + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2) + Reducer 3 <- Reducer 2 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcpart + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: ds (type: string), hr (type: string) + sort order: ++ + Map-reduce partition columns: ds (type: string), hr (type: string) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Map 4 + Map Operator Tree: + TableScan + alias: srcpart_date_hour + filterExpr: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean) + Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean) + Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: ds (type: string), hr (type: string) + sort order: ++ + Map-reduce partition columns: ds (type: string), hr (type: string) + Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 ds (type: string), hr (type: string) + 1 ds (type: string), hr (type: string) + Statistics: Num rows: 2200 Data size: 23372 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 + 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 + Execution mode: vectorized + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(*) from srcpart join srcpart_date_hour on (srcpart.ds = srcpart_date_hour.ds and srcpart.hr = srcpart_date_hour.hr) where srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11 +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +PREHOOK: Input: default@srcpart_date_hour +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from srcpart join srcpart_date_hour on (srcpart.ds = srcpart_date_hour.ds and srcpart.hr = srcpart_date_hour.hr) where srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +POSTHOOK: Input: default@srcpart_date_hour +#### A masked pattern was here #### +500 +PREHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_date_hour on (srcpart.ds = srcpart_date_hour.ds and srcpart.hr = srcpart_date_hour.hr) where srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11 +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_date_hour on (srcpart.ds = srcpart_date_hour.ds and srcpart.hr = srcpart_date_hour.hr) where srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11 +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 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2) + Reducer 3 <- Reducer 2 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcpart + filterExpr: (ds is not null and hr is not null) (type: boolean) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: ds (type: string), hr (type: string) + sort order: ++ + Map-reduce partition columns: ds (type: string), hr (type: string) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Map 4 + Map Operator Tree: + TableScan + alias: srcpart_date_hour + filterExpr: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean) + Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean) + Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: ds (type: string), hr (type: string) + sort order: ++ + Map-reduce partition columns: ds (type: string), hr (type: string) + Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 ds (type: string), hr (type: string) + 1 ds (type: string), hr (type: string) + Statistics: Num rows: 2200 Data size: 23372 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 + 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 + Execution mode: vectorized + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(*) from srcpart join srcpart_date_hour on (srcpart.ds = srcpart_date_hour.ds and srcpart.hr = srcpart_date_hour.hr) where srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11 +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +PREHOOK: Input: default@srcpart_date_hour +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from srcpart join srcpart_date_hour on (srcpart.ds = srcpart_date_hour.ds and srcpart.hr = srcpart_date_hour.hr) where srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +POSTHOOK: Input: default@srcpart_date_hour +#### A masked pattern was here #### +500 +PREHOOK: query: select count(*) from srcpart where ds = '2008-04-08' and hr = 11 +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from srcpart where ds = '2008-04-08' and hr = 11 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +#### A masked pattern was here #### +500 +PREHOOK: query: -- empty set +EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = 'I DONT EXIST' +PREHOOK: type: QUERY +POSTHOOK: query: -- empty set +EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = 'I DONT EXIST' +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-1 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Spark +#### A masked pattern was here #### + Vertices: + Map 5 + Map Operator Tree: + TableScan + alias: srcpart_date + filterExpr: (ds is not null and (date = 'I DONT EXIST')) (type: boolean) + Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (ds is not null and (date = 'I DONT EXIST')) (type: boolean) + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Spark Partition Pruning Sink Operator + partition key expr: ds + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + target column name: ds + target work: Map 1 + Execution mode: vectorized + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2) + Reducer 3 <- Reducer 2 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcpart + filterExpr: ds is not null (type: boolean) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: ds (type: string) + sort order: + + Map-reduce partition columns: ds (type: string) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Map 4 + Map Operator Tree: + TableScan + alias: srcpart_date + filterExpr: (ds is not null and (date = 'I DONT EXIST')) (type: boolean) + Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (ds is not null and (date = 'I DONT EXIST')) (type: boolean) + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: ds (type: string) + sort order: + + Map-reduce partition columns: ds (type: string) + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 ds (type: string) + 1 ds (type: string) + Statistics: Num rows: 2200 Data size: 23372 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 + 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 + Execution mode: vectorized + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = 'I DONT EXIST' +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +PREHOOK: Input: default@srcpart_date +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = 'I DONT EXIST' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +POSTHOOK: Input: default@srcpart_date +#### A masked pattern was here #### +0 +PREHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = 'I DONT EXIST' +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = 'I DONT EXIST' +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 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2) + Reducer 3 <- Reducer 2 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcpart + filterExpr: ds is not null (type: boolean) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: ds (type: string) + sort order: + + Map-reduce partition columns: ds (type: string) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Map 4 + Map Operator Tree: + TableScan + alias: srcpart_date + filterExpr: (ds is not null and (date = 'I DONT EXIST')) (type: boolean) + Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (ds is not null and (date = 'I DONT EXIST')) (type: boolean) + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: ds (type: string) + sort order: + + Map-reduce partition columns: ds (type: string) + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 ds (type: string) + 1 ds (type: string) + Statistics: Num rows: 2200 Data size: 23372 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 + 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 + Execution mode: vectorized + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = 'I DONT EXIST' +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +PREHOOK: Input: default@srcpart_date +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = 'I DONT EXIST' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +POSTHOOK: Input: default@srcpart_date +#### A masked pattern was here #### +0 +PREHOOK: query: select count(*) from srcpart where ds = 'I DONT EXIST' +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from srcpart where ds = 'I DONT EXIST' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +#### A masked pattern was here #### +0 +PREHOOK: query: -- expressions +EXPLAIN select count(*) from srcpart join srcpart_double_hour on (srcpart.hr = cast(srcpart_double_hour.hr/2 as int)) where srcpart_double_hour.hour = 11 +PREHOOK: type: QUERY +POSTHOOK: query: -- expressions +EXPLAIN select count(*) from srcpart join srcpart_double_hour on (srcpart.hr = cast(srcpart_double_hour.hr/2 as int)) where srcpart_double_hour.hour = 11 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-1 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Spark +#### A masked pattern was here #### + Vertices: + Map 5 + Map Operator Tree: + TableScan + alias: srcpart_double_hour + filterExpr: (UDFToDouble(UDFToInteger((hr / 2))) is not null and (hour = 11)) (type: boolean) + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (UDFToDouble(UDFToInteger((hr / 2))) is not null and (hour = 11)) (type: boolean) + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: UDFToDouble(UDFToInteger((hr / 2))) (type: double) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col0 (type: double) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Spark Partition Pruning Sink Operator + partition key expr: UDFToDouble(hr) + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + target column name: hr + target work: Map 1 + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2) + Reducer 3 <- Reducer 2 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcpart + filterExpr: UDFToDouble(hr) is not null (type: boolean) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: UDFToDouble(hr) is not null (type: boolean) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: UDFToDouble(hr) (type: double) + sort order: + + Map-reduce partition columns: UDFToDouble(hr) (type: double) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Map 4 + Map Operator Tree: + TableScan + alias: srcpart_double_hour + filterExpr: (UDFToDouble(UDFToInteger((hr / 2))) is not null and (hour = 11)) (type: boolean) + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (UDFToDouble(UDFToInteger((hr / 2))) is not null and (hour = 11)) (type: boolean) + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: UDFToDouble(UDFToInteger((hr / 2))) (type: double) + sort order: + + Map-reduce partition columns: UDFToDouble(UDFToInteger((hr / 2))) (type: double) + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 UDFToDouble(hr) (type: double) + 1 UDFToDouble(UDFToInteger((hr / 2))) (type: double) + Statistics: Num rows: 1100 Data size: 11686 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 + 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 + Execution mode: vectorized + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(*) from srcpart join srcpart_double_hour on (srcpart.hr = cast(srcpart_double_hour.hr/2 as int)) where srcpart_double_hour.hour = 11 +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +PREHOOK: Input: default@srcpart_double_hour +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from srcpart join srcpart_double_hour on (srcpart.hr = cast(srcpart_double_hour.hr/2 as int)) where srcpart_double_hour.hour = 11 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +POSTHOOK: Input: default@srcpart_double_hour +#### A masked pattern was here #### +1000 +PREHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_double_hour on (srcpart.hr*2 = srcpart_double_hour.hr) where srcpart_double_hour.hour = 11 +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_double_hour on (srcpart.hr*2 = srcpart_double_hour.hr) where srcpart_double_hour.hour = 11 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-1 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Spark +#### A masked pattern was here #### + Vertices: + Map 5 + Map Operator Tree: + TableScan + alias: srcpart_double_hour + filterExpr: (hr is not null and (hour = 11)) (type: boolean) + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (hr is not null and (hour = 11)) (type: boolean) + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: hr (type: double) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col0 (type: double) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Spark Partition Pruning Sink Operator + partition key expr: (hr * 2) + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + target column name: hr + target work: Map 1 + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2) + Reducer 3 <- Reducer 2 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcpart + filterExpr: (hr * 2) is not null (type: boolean) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (hr * 2) is not null (type: boolean) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: (hr * 2) (type: double) + sort order: + + Map-reduce partition columns: (hr * 2) (type: double) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Map 4 + Map Operator Tree: + TableScan + alias: srcpart_double_hour + filterExpr: (hr is not null and (hour = 11)) (type: boolean) + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (hr is not null and (hour = 11)) (type: boolean) + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: hr (type: double) + sort order: + + Map-reduce partition columns: hr (type: double) + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 (hr * 2) (type: double) + 1 hr (type: double) + Statistics: Num rows: 1100 Data size: 11686 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 + 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 + Execution mode: vectorized + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(*) from srcpart join srcpart_double_hour on (srcpart.hr*2 = srcpart_double_hour.hr) where srcpart_double_hour.hour = 11 +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +PREHOOK: Input: default@srcpart_double_hour +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from srcpart join srcpart_double_hour on (srcpart.hr*2 = srcpart_double_hour.hr) where srcpart_double_hour.hour = 11 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +POSTHOOK: Input: default@srcpart_double_hour +#### A masked pattern was here #### +1000 +PREHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_double_hour on (srcpart.hr = cast(srcpart_double_hour.hr/2 as int)) where srcpart_double_hour.hour = 11 +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_double_hour on (srcpart.hr = cast(srcpart_double_hour.hr/2 as int)) where srcpart_double_hour.hour = 11 +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 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2) + Reducer 3 <- Reducer 2 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcpart + filterExpr: UDFToDouble(hr) is not null (type: boolean) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: UDFToDouble(hr) is not null (type: boolean) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: UDFToDouble(hr) (type: double) + sort order: + + Map-reduce partition columns: UDFToDouble(hr) (type: double) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Map 4 + Map Operator Tree: + TableScan + alias: srcpart_double_hour + filterExpr: (UDFToDouble(UDFToInteger((hr / 2))) is not null and (hour = 11)) (type: boolean) + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (UDFToDouble(UDFToInteger((hr / 2))) is not null and (hour = 11)) (type: boolean) + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: UDFToDouble(UDFToInteger((hr / 2))) (type: double) + sort order: + + Map-reduce partition columns: UDFToDouble(UDFToInteger((hr / 2))) (type: double) + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 UDFToDouble(hr) (type: double) + 1 UDFToDouble(UDFToInteger((hr / 2))) (type: double) + Statistics: Num rows: 1100 Data size: 11686 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 + 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 + Execution mode: vectorized + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(*) from srcpart join srcpart_double_hour on (srcpart.hr = cast(srcpart_double_hour.hr/2 as int)) where srcpart_double_hour.hour = 11 +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +PREHOOK: Input: default@srcpart_double_hour +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from srcpart join srcpart_double_hour on (srcpart.hr = cast(srcpart_double_hour.hr/2 as int)) where srcpart_double_hour.hour = 11 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +POSTHOOK: Input: default@srcpart_double_hour +#### A masked pattern was here #### +1000 +PREHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_double_hour on (srcpart.hr*2 = srcpart_double_hour.hr) where srcpart_double_hour.hour = 11 +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_double_hour on (srcpart.hr*2 = srcpart_double_hour.hr) where srcpart_double_hour.hour = 11 +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 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2) + Reducer 3 <- Reducer 2 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcpart + filterExpr: (hr * 2) is not null (type: boolean) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (hr * 2) is not null (type: boolean) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: (hr * 2) (type: double) + sort order: + + Map-reduce partition columns: (hr * 2) (type: double) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Map 4 + Map Operator Tree: + TableScan + alias: srcpart_double_hour + filterExpr: (hr is not null and (hour = 11)) (type: boolean) + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (hr is not null and (hour = 11)) (type: boolean) + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: hr (type: double) + sort order: + + Map-reduce partition columns: hr (type: double) + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 (hr * 2) (type: double) + 1 hr (type: double) + Statistics: Num rows: 1100 Data size: 11686 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 + 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 + Execution mode: vectorized + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(*) from srcpart join srcpart_double_hour on (srcpart.hr*2 = srcpart_double_hour.hr) where srcpart_double_hour.hour = 11 +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +PREHOOK: Input: default@srcpart_double_hour +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from srcpart join srcpart_double_hour on (srcpart.hr*2 = srcpart_double_hour.hr) where srcpart_double_hour.hour = 11 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +POSTHOOK: Input: default@srcpart_double_hour +#### A masked pattern was here #### +1000 +PREHOOK: query: select count(*) from srcpart where hr = 11 +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from srcpart where hr = 11 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +#### A masked pattern was here #### +1000 +PREHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_double_hour on (cast(srcpart.hr*2 as string) = cast(srcpart_double_hour.hr as string)) where srcpart_double_hour.hour = 11 +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_double_hour on (cast(srcpart.hr*2 as string) = cast(srcpart_double_hour.hr as string)) where srcpart_double_hour.hour = 11 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-1 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Spark +#### A ma
<TRUNCATED>