PREHOOK: query: explain create table src_orc_merge_test_part(key int, value string) partitioned by (ds string, ts string) stored as orc PREHOOK: type: CREATETABLE POSTHOOK: query: explain create table src_orc_merge_test_part(key int, value string) partitioned by (ds string, ts string) stored as orc POSTHOOK: type: CREATETABLE Stage-0 Create Table Operator: columns:["key int","value string"] input format:org.apache.hadoop.hive.ql.io.orc.OrcInputFormat name:default.src_orc_merge_test_part output format:org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat partition columns:["ds string","ts string"] PREHOOK: query: create table src_orc_merge_test_part(key int, value string) partitioned by (ds string, ts string) stored as orc PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@src_orc_merge_test_part POSTHOOK: query: create table src_orc_merge_test_part(key int, value string) partitioned by (ds string, ts string) stored as orc POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@src_orc_merge_test_part PREHOOK: query: alter table src_orc_merge_test_part add partition (ds='2012-01-03', ts='2012-01-03+14:46:31') PREHOOK: type: ALTERTABLE_ADDPARTS PREHOOK: Output: default@src_orc_merge_test_part POSTHOOK: query: alter table src_orc_merge_test_part add partition (ds='2012-01-03', ts='2012-01-03+14:46:31') POSTHOOK: type: ALTERTABLE_ADDPARTS POSTHOOK: Output: default@src_orc_merge_test_part POSTHOOK: Output: default@src_orc_merge_test_part@ds=2012-01-03/ts=2012-01-03+14%3A46%3A31 PREHOOK: query: desc extended src_orc_merge_test_part partition (ds='2012-01-03', ts='2012-01-03+14:46:31') PREHOOK: type: DESCTABLE PREHOOK: Input: default@src_orc_merge_test_part POSTHOOK: query: desc extended src_orc_merge_test_part partition (ds='2012-01-03', ts='2012-01-03+14:46:31') POSTHOOK: type: DESCTABLE POSTHOOK: Input: default@src_orc_merge_test_part key int value string ds string ts string # Partition Information # col_name data_type comment ds string ts string #### A masked pattern was here #### PREHOOK: query: explain insert overwrite table src_orc_merge_test_part partition(ds='2012-01-03', ts='2012-01-03+14:46:31') select * from src PREHOOK: type: QUERY POSTHOOK: query: explain insert overwrite table src_orc_merge_test_part partition(ds='2012-01-03', ts='2012-01-03+14:46:31') select * from src POSTHOOK: type: QUERY Plan optimized by CBO. Stage-3 Stats-Aggr Operator Stage-0 Move Operator partition:{"ts":"2012-01-03+14:46:31","ds":"2012-01-03"} table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.src_orc_merge_test_part","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} Stage-2 Dependency Collection{} Stage-1 Map 1 File Output Operator [FS_3] compressed:false Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.src_orc_merge_test_part","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} Select Operator [SEL_1] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE TableScan [TS_0] alias:src Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: insert overwrite table src_orc_merge_test_part partition(ds='2012-01-03', ts='2012-01-03+14:46:31') select * from src PREHOOK: type: QUERY PREHOOK: Input: default@src PREHOOK: Output: default@src_orc_merge_test_part@ds=2012-01-03/ts=2012-01-03+14%3A46%3A31 POSTHOOK: query: insert overwrite table src_orc_merge_test_part partition(ds='2012-01-03', ts='2012-01-03+14:46:31') select * from src POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@src_orc_merge_test_part@ds=2012-01-03/ts=2012-01-03+14%3A46%3A31 POSTHOOK: Lineage: src_orc_merge_test_part PARTITION(ds=2012-01-03,ts=2012-01-03+14:46:31).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: src_orc_merge_test_part PARTITION(ds=2012-01-03,ts=2012-01-03+14:46:31).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: explain insert into table src_orc_merge_test_part partition(ds='2012-01-03', ts='2012-01-03+14:46:31') select * from src limit 100 PREHOOK: type: QUERY POSTHOOK: query: explain insert into table src_orc_merge_test_part partition(ds='2012-01-03', ts='2012-01-03+14:46:31') select * from src limit 100 POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Stage-3 Stats-Aggr Operator Stage-0 Move Operator partition:{"ts":"2012-01-03+14:46:31","ds":"2012-01-03"} table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.src_orc_merge_test_part","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} Stage-2 Dependency Collection{} Stage-1 Reducer 2 File Output Operator [FS_7] compressed:false Statistics:Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.src_orc_merge_test_part","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} Select Operator [SEL_6] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE Limit [LIM_5] Number of rows:100 Statistics:Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE Select Operator [SEL_4] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_3] sort order: Statistics:Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE value expressions:_col0 (type: string), _col1 (type: string) Limit [LIM_2] Number of rows:100 Statistics:Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE Select Operator [SEL_1] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE TableScan [TS_0] alias:src Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: explain select count(1) from src_orc_merge_test_part where ds='2012-01-03' and ts='2012-01-03+14:46:31' PREHOOK: type: QUERY POSTHOOK: query: explain select count(1) from src_orc_merge_test_part where ds='2012-01-03' and ts='2012-01-03+14:46:31' POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_8] compressed:false Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Group By Operator [GBY_6] | aggregations:["count(VALUE._col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_5] sort order: Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions:_col0 (type: bigint) Group By Operator [GBY_4] aggregations:["count(1)"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator [SEL_2] Statistics:Num rows: 500 Data size: 47000 Basic stats: COMPLETE Column stats: NONE TableScan [TS_0] alias:src_orc_merge_test_part Statistics:Num rows: 500 Data size: 47000 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: explain select sum(hash(key)), sum(hash(value)) from src_orc_merge_test_part where ds='2012-01-03' and ts='2012-01-03+14:46:31' PREHOOK: type: QUERY POSTHOOK: query: explain select sum(hash(key)), sum(hash(value)) from src_orc_merge_test_part where ds='2012-01-03' and ts='2012-01-03+14:46:31' POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_8] compressed:false Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Group By Operator [GBY_6] | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_5] sort order: Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE value expressions:_col0 (type: bigint), _col1 (type: bigint) Group By Operator [GBY_4] aggregations:["sum(_col0)","sum(_col1)"] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Select Operator [SEL_2] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 500 Data size: 47000 Basic stats: COMPLETE Column stats: NONE TableScan [TS_0] alias:src_orc_merge_test_part Statistics:Num rows: 500 Data size: 47000 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: alter table src_orc_merge_test_part partition (ds='2012-01-03', ts='2012-01-03+14:46:31') concatenate PREHOOK: type: ALTER_PARTITION_MERGE PREHOOK: Input: default@src_orc_merge_test_part PREHOOK: Output: default@src_orc_merge_test_part@ds=2012-01-03/ts=2012-01-03+14%3A46%3A31 POSTHOOK: query: alter table src_orc_merge_test_part partition (ds='2012-01-03', ts='2012-01-03+14:46:31') concatenate POSTHOOK: type: ALTER_PARTITION_MERGE POSTHOOK: Input: default@src_orc_merge_test_part POSTHOOK: Output: default@src_orc_merge_test_part@ds=2012-01-03/ts=2012-01-03+14%3A46%3A31 PREHOOK: query: explain select count(1) from src_orc_merge_test_part where ds='2012-01-03' and ts='2012-01-03+14:46:31' PREHOOK: type: QUERY POSTHOOK: query: explain select count(1) from src_orc_merge_test_part where ds='2012-01-03' and ts='2012-01-03+14:46:31' POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_8] compressed:false Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Group By Operator [GBY_6] | aggregations:["count(VALUE._col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_5] sort order: Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions:_col0 (type: bigint) Group By Operator [GBY_4] aggregations:["count(1)"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator [SEL_2] Statistics:Num rows: 0 Data size: 2527 Basic stats: PARTIAL Column stats: NONE TableScan [TS_0] alias:src_orc_merge_test_part Statistics:Num rows: 0 Data size: 2527 Basic stats: PARTIAL Column stats: NONE PREHOOK: query: explain select sum(hash(key)), sum(hash(value)) from src_orc_merge_test_part where ds='2012-01-03' and ts='2012-01-03+14:46:31' PREHOOK: type: QUERY POSTHOOK: query: explain select sum(hash(key)), sum(hash(value)) from src_orc_merge_test_part where ds='2012-01-03' and ts='2012-01-03+14:46:31' POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_8] compressed:false Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Group By Operator [GBY_6] | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_5] sort order: Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE value expressions:_col0 (type: bigint), _col1 (type: bigint) Group By Operator [GBY_4] aggregations:["sum(_col0)","sum(_col1)"] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Select Operator [SEL_2] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 24 Data size: 2527 Basic stats: COMPLETE Column stats: NONE TableScan [TS_0] alias:src_orc_merge_test_part Statistics:Num rows: 24 Data size: 2527 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: drop table src_orc_merge_test_part PREHOOK: type: DROPTABLE PREHOOK: Input: default@src_orc_merge_test_part PREHOOK: Output: default@src_orc_merge_test_part POSTHOOK: query: drop table src_orc_merge_test_part POSTHOOK: type: DROPTABLE POSTHOOK: Input: default@src_orc_merge_test_part POSTHOOK: Output: default@src_orc_merge_test_part Warning: Map Join MAPJOIN[20][bigTable=?] in task 'Map 1' is a cross product PREHOOK: query: explain select sum(hash(a.k1,a.v1,a.k2, a.v2)) from ( select src1.key as k1, src1.value as v1, src2.key as k2, src2.value as v2 FROM (select * FROM src WHERE src.key < 10) src1 JOIN (select * FROM src WHERE src.key < 10) src2 SORT BY k1, v1, k2, v2 ) a PREHOOK: type: QUERY POSTHOOK: query: explain select sum(hash(a.k1,a.v1,a.k2, a.v2)) from ( select src1.key as k1, src1.value as v1, src2.key as k2, src2.value as v2 FROM (select * FROM src WHERE src.key < 10) src1 JOIN (select * FROM src WHERE src.key < 10) src2 SORT BY k1, v1, k2, v2 ) a POSTHOOK: type: QUERY Plan not optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Map 1 <- Map 4 (BROADCAST_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 3 File Output Operator [FS_17] compressed:false Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Group By Operator [GBY_15] | aggregations:["sum(VALUE._col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_14] sort order: Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions:_col0 (type: bigint) Group By Operator [GBY_13] aggregations:["sum(hash(_col0,_col1,_col2,_col3))"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator [SEL_11] | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_10] key expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) sort order:++++ Statistics:Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE Map Join Operator [MAPJOIN_20] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{} | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE |<-Map 4 [BROADCAST_EDGE] | Reduce Output Operator [RS_7] | sort order: | Statistics:Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE | value expressions:_col0 (type: string), _col1 (type: string) | Select Operator [SEL_5] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE | Filter Operator [FIL_19] | predicate:(key < 10) (type: boolean) | Statistics:Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_3] | alias:src | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE |<-Select Operator [SEL_2] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Filter Operator [FIL_18] predicate:(key < 10) (type: boolean) Statistics:Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE TableScan [TS_0] alias:src Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: explain select key, (c_int+1)+2 as x, sum(c_int) from cbo_t1 group by c_float, cbo_t1.c_int, key PREHOOK: type: QUERY POSTHOOK: query: explain select key, (c_int+1)+2 as x, sum(c_int) from cbo_t1 group by c_float, cbo_t1.c_int, key POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_7] compressed:false Statistics:Num rows: 10 Data size: 885 Basic stats: COMPLETE Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_6] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 10 Data size: 885 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator [GBY_5] | aggregations:["sum(VALUE._col0)"] | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_4] key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) sort order:+++ Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col3 (type: bigint) Group By Operator [GBY_3] aggregations:["sum(_col1)"] keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_1] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_0] alias:cbo_t1 Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select x, y, count(*) from (select key, (c_int+c_float+1+2) as x, sum(c_int) as y from cbo_t1 group by c_float, cbo_t1.c_int, key) R group by y, x PREHOOK: type: QUERY POSTHOOK: query: explain select x, y, count(*) from (select key, (c_int+c_float+1+2) as x, sum(c_int) as y from cbo_t1 group by c_float, cbo_t1.c_int, key) R group by y, x POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 3 File Output Operator [FS_12] compressed:false Statistics:Num rows: 5 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_11] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 5 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator [GBY_10] | aggregations:["count(VALUE._col0)"] | keys:KEY._col0 (type: bigint), KEY._col1 (type: float) | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 5 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_9] key expressions:_col0 (type: bigint), _col1 (type: float) Map-reduce partition columns:_col0 (type: bigint), _col1 (type: float) sort order:++ Statistics:Num rows: 5 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col2 (type: bigint) Group By Operator [GBY_8] aggregations:["count()"] keys:_col0 (type: bigint), _col1 (type: float) outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 5 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_6] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator [GBY_5] | aggregations:["sum(VALUE._col0)"] | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_4] key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) sort order:+++ Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col3 (type: bigint) Group By Operator [GBY_3] aggregations:["sum(_col1)"] keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_1] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_0] alias:cbo_t1 Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key order by a) cbo_t1 join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key order by q/10 desc, r asc) cbo_t2 on cbo_t1.a=p join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 0) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c order by cbo_t3.c_int+c desc, c PREHOOK: type: QUERY POSTHOOK: query: explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key order by a) cbo_t1 join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key order by q/10 desc, r asc) cbo_t2 on cbo_t1.a=p join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 0) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c order by cbo_t3.c_int+c desc, c POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Reducer 11 <- Reducer 10 (SIMPLE_EDGE) Reducer 10 <- Map 9 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE) Reducer 7 <- Reducer 6 (SIMPLE_EDGE) Reducer 6 <- Map 5 (SIMPLE_EDGE) Reducer 8 <- Reducer 11 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 4 File Output Operator [FS_47] compressed:false Statistics:Num rows: 6 Data size: 494 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_46] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 6 Data size: 494 Basic stats: COMPLETE Column stats: NONE |<-Reducer 3 [SIMPLE_EDGE] Reduce Output Operator [RS_45] key expressions:(UDFToLong(_col0) + _col1) (type: bigint), _col1 (type: bigint) sort order:-+ Statistics:Num rows: 6 Data size: 494 Basic stats: COMPLETE Column stats: NONE value expressions:_col0 (type: int), _col2 (type: bigint) Group By Operator [GBY_43] | aggregations:["count(VALUE._col0)"] | keys:KEY._col0 (type: int), KEY._col1 (type: bigint) | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 6 Data size: 494 Basic stats: COMPLETE Column stats: NONE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_42] key expressions:_col0 (type: int), _col1 (type: bigint) Map-reduce partition columns:_col0 (type: int), _col1 (type: bigint) sort order:++ Statistics:Num rows: 12 Data size: 989 Basic stats: COMPLETE Column stats: NONE value expressions:_col2 (type: bigint) Group By Operator [GBY_41] aggregations:["count()"] keys:_col0 (type: int), _col1 (type: bigint) outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 12 Data size: 989 Basic stats: COMPLETE Column stats: NONE Select Operator [SEL_37] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 12 Data size: 989 Basic stats: COMPLETE Column stats: NONE Filter Operator [FIL_53] predicate:((_col3 > 0) or (_col1 >= 0)) (type: boolean) Statistics:Num rows: 12 Data size: 989 Basic stats: COMPLETE Column stats: NONE Merge Join Operator [MERGEJOIN_59] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} | outputColumnNames:["_col1","_col3","_col4"] | Statistics:Num rows: 19 Data size: 1566 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_33] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col1 (type: int) | Select Operator [SEL_1] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_54] | predicate:key is not null (type: boolean) | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:cbo_t3 | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 8 [SIMPLE_EDGE] Reduce Output Operator [RS_35] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE value expressions:_col1 (type: int), _col2 (type: bigint) Select Operator [SEL_29] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE Filter Operator [FIL_55] predicate:((_col3 + _col1) >= 0) (type: boolean) Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE Merge Join Operator [MERGEJOIN_58] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} | outputColumnNames:["_col1","_col2","_col3","_col4"] | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 11 [SIMPLE_EDGE] | Reduce Output Operator [RS_27] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col1 (type: int), _col2 (type: bigint) | Select Operator [SEL_22] | | outputColumnNames:["_col0","_col1","_col2"] | | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE | |<-Reducer 10 [SIMPLE_EDGE] | Reduce Output Operator [RS_21] | key expressions:_col0 (type: string) | sort order:+ | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col1 (type: int), _col2 (type: bigint) | Select Operator [SEL_20] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE | Group By Operator [GBY_19] | | aggregations:["sum(VALUE._col0)"] | | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) | | outputColumnNames:["_col0","_col1","_col2","_col3"] | | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE | |<-Map 9 [SIMPLE_EDGE] | Reduce Output Operator [RS_18] | key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) | Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) | sort order:+++ | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col3 (type: bigint) | Group By Operator [GBY_17] | aggregations:["sum(_col1)"] | keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_15] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_57] | predicate:((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and key is not null) (type: boolean) | Statistics:Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_13] | alias:cbo_t1 | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 7 [SIMPLE_EDGE] Reduce Output Operator [RS_25] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: int) Select Operator [SEL_11] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 6 [SIMPLE_EDGE] Reduce Output Operator [RS_10] key expressions:_col3 (type: double), _col2 (type: bigint) sort order:-+ Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: string), _col1 (type: int) Select Operator [SEL_9] outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator [GBY_8] | aggregations:["sum(VALUE._col0)"] | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 5 [SIMPLE_EDGE] Reduce Output Operator [RS_7] key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) sort order:+++ Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col3 (type: bigint) Group By Operator [GBY_6] aggregations:["sum(_col1)"] keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_4] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator [FIL_56] predicate:((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and key is not null) (type: boolean) Statistics:Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_2] alias:cbo_t2 Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by b % c asc, b desc) cbo_t1 left outer join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0) cbo_t2 on cbo_t1.a=p left outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 0) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c having cbo_t3.c_int > 0 and (c_int >=1 or c >= 1) and (c_int + c) >= 0 order by cbo_t3.c_int % c asc, cbo_t3.c_int desc PREHOOK: type: QUERY POSTHOOK: query: explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by b % c asc, b desc) cbo_t1 left outer join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0) cbo_t2 on cbo_t1.a=p left outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 0) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c having cbo_t3.c_int > 0 and (c_int >=1 or c >= 1) and (c_int + c) >= 0 order by cbo_t3.c_int % c asc, cbo_t3.c_int desc POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) Reducer 5 <- Reducer 4 (SIMPLE_EDGE) Reducer 4 <- Map 10 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) Reducer 6 <- Reducer 5 (SIMPLE_EDGE) Reducer 9 <- Reducer 8 (SIMPLE_EDGE) Reducer 8 <- Map 7 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 6 File Output Operator [FS_42] compressed:false Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_41] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE |<-Reducer 5 [SIMPLE_EDGE] Reduce Output Operator [RS_40] key expressions:(UDFToLong(_col0) % _col1) (type: bigint), _col0 (type: int) sort order:+- Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE value expressions:_col1 (type: bigint), _col2 (type: bigint) Group By Operator [GBY_38] | aggregations:["count(VALUE._col0)"] | keys:KEY._col0 (type: int), KEY._col1 (type: bigint) | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE |<-Reducer 4 [SIMPLE_EDGE] Reduce Output Operator [RS_37] key expressions:_col0 (type: int), _col1 (type: bigint) Map-reduce partition columns:_col0 (type: int), _col1 (type: bigint) sort order:++ Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE value expressions:_col2 (type: bigint) Group By Operator [GBY_36] aggregations:["count()"] keys:_col0 (type: int), _col1 (type: bigint) outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator [SEL_34] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Filter Operator [FIL_33] predicate:(((_col1 > 0) or (_col6 >= 0)) and (((_col6 >= 1) or (_col2 >= 1)) and ((UDFToLong(_col6) + _col2) >= 0))) (type: boolean) Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Merge Join Operator [MERGEJOIN_52] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} | outputColumnNames:["_col1","_col2","_col6"] | Statistics:Num rows: 5 Data size: 391 Basic stats: COMPLETE Column stats: NONE |<-Map 10 [SIMPLE_EDGE] | Reduce Output Operator [RS_31] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 5 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col1 (type: int) | Select Operator [SEL_27] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 5 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_50] | predicate:((c_int > 0) and key is not null) (type: boolean) | Statistics:Num rows: 5 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_25] | alias:cbo_t3 | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 3 [SIMPLE_EDGE] Reduce Output Operator [RS_29] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE value expressions:_col1 (type: int), _col2 (type: bigint) Select Operator [SEL_22] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Filter Operator [FIL_47] predicate:((_col3 + _col1) >= 0) (type: boolean) Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Merge Join Operator [MERGEJOIN_51] | condition map:[{"":"Right Outer Join0 to 1"}] | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} | outputColumnNames:["_col1","_col2","_col3","_col4"] | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE |<-Reducer 2 [SIMPLE_EDGE] | Reduce Output Operator [RS_19] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE | value expressions:_col1 (type: int) | Select Operator [SEL_7] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE | Group By Operator [GBY_6] | | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) | | outputColumnNames:["_col0","_col1","_col2"] | | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE | |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_5] | key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) | Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) | sort order:+++ | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE | Group By Operator [GBY_4] | keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE | Select Operator [SEL_2] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE | Filter Operator [FIL_48] | predicate:(((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) and key is not null) (type: boolean) | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE | TableScan [TS_0] | alias:cbo_t2 | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 9 [SIMPLE_EDGE] Reduce Output Operator [RS_20] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE value expressions:_col1 (type: int), _col2 (type: bigint) Select Operator [SEL_17] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE |<-Reducer 8 [SIMPLE_EDGE] Reduce Output Operator [RS_16] key expressions:_col3 (type: bigint), _col1 (type: int) sort order:+- Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE value expressions:_col0 (type: string), _col2 (type: bigint) Select Operator [SEL_15] outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE Group By Operator [GBY_14] | aggregations:["sum(VALUE._col0)"] | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE |<-Map 7 [SIMPLE_EDGE] Reduce Output Operator [RS_13] key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) sort order:+++ Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE value expressions:_col3 (type: bigint) Group By Operator [GBY_12] aggregations:["sum(_col1)"] keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE Select Operator [SEL_10] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE Filter Operator [FIL_49] predicate:(((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) and key is not null) (type: boolean) Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE TableScan [TS_8] alias:cbo_t1 Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by b+c, a desc) cbo_t1 right outer join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0) cbo_t2 on cbo_t1.a=p right outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 2) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c PREHOOK: type: QUERY POSTHOOK: query: explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by b+c, a desc) cbo_t1 right outer join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0) cbo_t2 on cbo_t1.a=p right outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 2) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) Reducer 5 <- Reducer 4 (SIMPLE_EDGE) Reducer 4 <- Map 9 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) Reducer 7 <- Map 6 (SIMPLE_EDGE) Reducer 8 <- Reducer 7 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 5 File Output Operator [FS_35] compressed:false Statistics:Num rows: 2 Data size: 160 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Group By Operator [GBY_33] | aggregations:["count(VALUE._col0)"] | keys:KEY._col0 (type: int), KEY._col1 (type: bigint) | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 2 Data size: 160 Basic stats: COMPLETE Column stats: NONE |<-Reducer 4 [SIMPLE_EDGE] Reduce Output Operator [RS_32] key expressions:_col0 (type: int), _col1 (type: bigint) Map-reduce partition columns:_col0 (type: int), _col1 (type: bigint) sort order:++ Statistics:Num rows: 4 Data size: 320 Basic stats: COMPLETE Column stats: NONE value expressions:_col2 (type: bigint) Group By Operator [GBY_31] aggregations:["count()"] keys:_col0 (type: int), _col1 (type: bigint) outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 4 Data size: 320 Basic stats: COMPLETE Column stats: NONE Select Operator [SEL_29] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 4 Data size: 320 Basic stats: COMPLETE Column stats: NONE Filter Operator [FIL_39] predicate:(((_col1 + _col4) >= 2) and ((_col1 > 0) or (_col6 >= 0))) (type: boolean) Statistics:Num rows: 4 Data size: 320 Basic stats: COMPLETE Column stats: NONE Merge Join Operator [MERGEJOIN_44] | condition map:[{"":"Right Outer Join0 to 1"}] | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} | outputColumnNames:["_col1","_col2","_col4","_col6"] | Statistics:Num rows: 22 Data size: 1762 Basic stats: COMPLETE Column stats: NONE |<-Map 9 [SIMPLE_EDGE] | Reduce Output Operator [RS_26] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col1 (type: int) | Select Operator [SEL_24] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_23] | alias:cbo_t3 | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 3 [SIMPLE_EDGE] Reduce Output Operator [RS_25] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE value expressions:_col1 (type: int), _col2 (type: bigint), _col4 (type: int) Select Operator [SEL_22] outputColumnNames:["_col0","_col1","_col2","_col4"] Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Merge Join Operator [MERGEJOIN_43] | condition map:[{"":"Left Outer Join0 to 1"}] | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} | outputColumnNames:["_col1","_col2","_col3","_col4"] | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE |<-Reducer 2 [SIMPLE_EDGE] | Reduce Output Operator [RS_19] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE | value expressions:_col1 (type: int) | Select Operator [SEL_7] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE | Group By Operator [GBY_6] | | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) | | outputColumnNames:["_col0","_col1","_col2"] | | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE | |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_5] | key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) | Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) | sort order:+++ | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE | Group By Operator [GBY_4] | keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE | Select Operator [SEL_2] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE | Filter Operator [FIL_41] | predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean) | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE | TableScan [TS_0] | alias:cbo_t2 | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 8 [SIMPLE_EDGE] Reduce Output Operator [RS_20] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE value expressions:_col1 (type: int), _col2 (type: bigint) Select Operator [SEL_17] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE |<-Reducer 7 [SIMPLE_EDGE] Reduce Output Operator [RS_16] key expressions:_col3 (type: bigint), _col0 (type: string) sort order:+- Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE value expressions:_col1 (type: int), _col2 (type: bigint) Select Operator [SEL_15] outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE Group By Operator [GBY_14] | aggregations:["sum(VALUE._col0)"] | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE |<-Map 6 [SIMPLE_EDGE] Reduce Output Operator [RS_13] key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) sort order:+++ Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE value expressions:_col3 (type: bigint) Group By Operator [GBY_12] aggregations:["sum(_col1)"] keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE Select Operator [SEL_10] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE Filter Operator [FIL_42] predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean) Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE TableScan [TS_8] alias:cbo_t1 Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by c+a desc) cbo_t1 full outer join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by p+q desc, r asc) cbo_t2 on cbo_t1.a=p full outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 0) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c having cbo_t3.c_int > 0 and (c_int >=1 or c >= 1) and (c_int + c) >= 0 order by cbo_t3.c_int PREHOOK: type: QUERY POSTHOOK: query: explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by c+a desc) cbo_t1 full outer join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by p+q desc, r asc) cbo_t2 on cbo_t1.a=p full outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 0) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c having cbo_t3.c_int > 0 and (c_int >=1 or c >= 1) and (c_int + c) >= 0 order by cbo_t3.c_int POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Reducer 10 <- Reducer 9 (SIMPLE_EDGE) Reducer 5 <- Map 11 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) Reducer 4 <- Reducer 10 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) Reducer 7 <- Reducer 6 (SIMPLE_EDGE) Reducer 6 <- Reducer 5 (SIMPLE_EDGE) Reducer 9 <- Map 8 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 7 File Output Operator [FS_41] compressed:false Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_40] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE |<-Reducer 6 [SIMPLE_EDGE] Reduce Output Operator [RS_39] key expressions:_col0 (type: int) sort order:+ Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE value expressions:_col1 (type: bigint), _col2 (type: bigint) Group By Operator [GBY_37] | aggregations:["count(VALUE._col0)"] | keys:KEY._col0 (type: int), KEY._col1 (type: bigint) | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE |<-Reducer 5 [SIMPLE_EDGE] Reduce Output Operator [RS_36] key expressions:_col0 (type: int), _col1 (type: bigint) Map-reduce partition columns:_col0 (type: int), _col1 (type: bigint) sort order:++ Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE value expressions:_col2 (type: bigint) Group By Operator [GBY_35] aggregations:["count()"] keys:_col0 (type: int), _col1 (type: bigint) outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator [SEL_33] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Filter Operator [FIL_44] predicate:(((((_col1 + _col4) >= 0) and ((_col1 > 0) or (_col6 >= 0))) and ((_col6 >= 1) or (_col2 >= 1))) and ((UDFToLong(_col6) + _col2) >= 0)) (type: boolean) Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Merge Join Operator [MERGEJOIN_50] | condition map:[{"":"Right Outer Join0 to 1"}] | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} | outputColumnNames:["_col1","_col2","_col4","_col6"] | Statistics:Num rows: 6 Data size: 489 Basic stats: COMPLETE Column stats: NONE |<-Map 11 [SIMPLE_EDGE] | Reduce Output Operator [RS_30] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 6 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col1 (type: int) | Select Operator [SEL_28] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 6 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_48] | predicate:(c_int > 0) (type: boolean) | Statistics:Num rows: 6 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_26] | alias:cbo_t3 | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 4 [SIMPLE_EDGE] Reduce Output Operator [RS_29] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE value expressions:_col1 (type: int), _col2 (type: bigint), _col4 (type: int) Select Operator [SEL_25] outputColumnNames:["_col0","_col1","_col2","_col4"] Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Merge Join Operator [MERGEJOIN_49] | condition map:[{"":"Outer Join 0 to 1"}] | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} | outputColumnNames:["_col1","_col2","_col3","_col4"] | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE |<-Reducer 10 [SIMPLE_EDGE] | Reduce Output Operator [RS_23] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE | value expressions:_col1 (type: int), _col2 (type: bigint) | Select Operator [SEL_20] | | outputColumnNames:["_col0","_col1","_col2"] | | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE | |<-Reducer 9 [SIMPLE_EDGE] | Reduce Output Operator [RS_19] | key expressions:_col3 (type: double) | sort order:- | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE | value expressions:_col0 (type: string), _col1 (type: int), _col2 (type: bigint) | Select Operator [SEL_18] | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE | Group By Operator [GBY_17] | | aggregations:["sum(VALUE._col0)"] | | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) | | outputColumnNames:["_col0","_col1","_col2","_col3"] | | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE | |<-Map 8 [SIMPLE_EDGE] | Reduce Output Operator [RS_16] | key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) | Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) | sort order:+++ | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE | value expressions:_col3 (type: bigint) | Group By Operator [GBY_15] | aggregations:["sum(_col1)"] | keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE | Select Operator [SEL_13] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE | Filter Operator [FIL_47] | predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean) | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE | TableScan [TS_11] | alias:cbo_t1 | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 3 [SIMPLE_EDGE] Reduce Output Operator [RS_22] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE value expressions:_col1 (type: int) Select Operator [SEL_9] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_8] key expressions:_col3 (type: double), _col2 (type: bigint) sort order:-+ Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE value expressions:_col0 (type: string), _col1 (type: int) Select Operator [SEL_7] outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE Group By Operator [GBY_6] | aggregations:["sum(VALUE._col0)"] | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_5] key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) sort order:+++ Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE value expressions:_col3 (type: bigint) Group By Operator [GBY_4] aggregations:["sum(_col1)"] keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE Select Operator [SEL_2] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE Filter Operator [FIL_46] predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean) Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE TableScan [TS_0] alias:cbo_t2 Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0) cbo_t1 join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0) cbo_t2 on cbo_t1.a=p join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 0) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c PREHOOK: type: QUERY POSTHOOK: query: explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0) cbo_t1 join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0) cbo_t2 on cbo_t1.a=p join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 0) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Reducer 5 <- Map 4 (SIMPLE_EDGE) Reducer 6 <- Reducer 5 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) Reducer 8 <- Map 7 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 3 File Output Operator [FS_39] compressed:false Statistics:Num rows: 6 Data size: 494 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Group By Operator [GBY_37] | aggregations:["count(VALUE._col0)"] | keys:KEY._col0 (type: int), KEY._col1 (type: bigint) | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 6 Data size: 494 Basic stats: COMPLETE Column stats: NONE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_36] key expressions:_col0 (type: int), _col1 (type: bigint) Map-reduce partition columns:_col0 (type: int), _col1 (type: bigint) sort order:++ Statistics:Num rows: 12 Data size: 989 Basic stats: COMPLETE Column stats: NONE value expressions:_col2 (type: bigint) Group By Operator [GBY_35] aggregations:["count()"] keys:_col0 (type: int), _col1 (type: bigint) outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 12 Data size: 989 Basic stats: COMPLETE Column stats: NONE Select Operator [SEL_31] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 12 Data size: 989 Basic stats: COMPLETE Column stats: NONE Filter Operator [FIL_45] predicate:((_col3 > 0) or (_col1 >= 0)) (type: boolean) Statistics:Num rows: 12 Data size: 989 Basic stats: COMPLETE Column stats: NONE Merge Join Operator [MERGEJOIN_51] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} | outputColumnNames:["_col1","_col3","_col4"] | Statistics:Num rows: 19 Data size: 1566 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_27] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col1 (type: int) | Select Operator [SEL_1] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_46] | predicate:key is not null (type: boolean) | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:cbo_t3 | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 6 [SIMPLE_EDGE] Reduce Output Operator [RS_29] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE value expressions:_col1 (type: int), _col2 (type: bigint) Select Operator [SEL_23] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Filter Operator [FIL_47] predicate:((_col3 + _col1) >= 0) (type: boolean) Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Merge Join Operator [MERGEJOIN_50] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} | outputColumnNames:["_col1","_col2","_col3","_col4"] | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE |<-Reducer 5 [SIMPLE_EDGE] | Reduce Output Operator [RS_19] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE | value expressions:_col1 (type: int) | Select Operator [SEL_9] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE | Group By Operator [GBY_8] | | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) | | outputColumnNames:["_col0","_col1","_col2"] | | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE | |<-Map 4 [SIMPLE_EDGE] | Reduce Output Operator [RS_7] | key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) | Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) | sort order:+++ | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE | Group By Operator [GBY_6] | keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE | Select Operator [SEL_4] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE | Filter Operator [FIL_48] | predicate:(((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) and key is not null) (type: boolean) | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE | TableScan [TS_2] | alias:cbo_t2 | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 8 [SIMPLE_EDGE] Reduce Output Operator [RS_21] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE value expressions:_col1 (type: int), _col2 (type: bigint) Select Operator [SEL_17] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE Group By Operator [GBY_16] | aggregations:["sum(VALUE._col0)"] | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE |<-Map 7 [SIMPLE_EDGE] Reduce Output Operator [RS_15] key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) sort order:+++ Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE value expressions:_col3 (type: bigint) Group By Operator [GBY_14] aggregations:["sum(_col1)"] keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE Select Operator [SEL_12] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE Filter Operator [FIL_49] predicate:(((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) and key is not null) (type: boolean) Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE TableScan [TS_10] alias:cbo_t1 Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select unionsrc.key FROM (select 'tst1' as key, count(1) as value from src) unionsrc PREHOOK: type: QUERY POSTHOOK: query: explain select unionsrc.key FROM (select 'tst1' as key, count(1) as value from src) unionsrc POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_8] compressed:false Statistics:Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_6] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator [GBY_5] | aggregations:["count(VALUE._col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_4] sort order: Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: bigint) Group By Operator [GBY_3] aggregations:["count(1)"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_1] Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_0] alias:src Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select unionsrc.key FROM (select 'max' as key, max(c_int) as value from cbo_t3 s1 UNION ALL select 'min' as key, min(c_int) as value from cbo_t3 s2 UNION ALL select 'avg' as key, avg(c_int) as value from cbo_t3 s3) unionsrc order by unionsrc.key PREHOOK: type: QUERY POSTHOOK: query: explain select unionsrc.key FROM (select 'max' as key, max(c_int) as value from cbo_t3 s1 UNION ALL select 'min' as key, min(c_int) as value from cbo_t3 s2 UNION ALL select 'avg' as key, avg(c_int) as value from cbo_t3 s3) unionsrc order by unionsrc.key POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Union 3 (CONTAINS) Reducer 4 <- Union 3 (SIMPLE_EDGE) Reducer 6 <- Map 5 (SIMPLE_EDGE), Union 3 (CONTAINS) Reducer 8 <- Map 7 (SIMPLE_EDGE), Union 3 (CONTAINS) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 4 File Output Operator [FS_29] compressed:false Statistics:Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_28] | outputColumnNames:["_col0"] | Statistics:Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE |<-Union 3 [SIMPLE_EDGE] |<-Reducer 2 [CONTAINS] | Reduce Output Operator [RS_27] | key expressions:_col0 (type: string) | sort order:+ | Select Operator [SEL_6] | outputColumnNames:["_col0"] | Group By Operator [GBY_5] | | aggregations:["count(VALUE._col0)"] | | outputColumnNames:["_col0"] | |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_4] | sort order: | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col0 (type: bigint) | Group By Operator [GBY_3] | aggregations:["count(_col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_1] | outputColumnNames:["_col0"] | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:s1 | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 6 [CONTAINS] | Reduce Output Operator [RS_27] | key expressions:_col0 (type: string) | sort order:+ | Select Operator [SEL_14] | outputColumnNames:["_col0"] | Group By Operator [GBY_13] | | aggregations:["count(VALUE._col0)"] | | outputColumnNames:["_col0"] | |<-Map 5 [SIMPLE_EDGE] | Reduce Output Operator [RS_12] | sort order: | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col0 (type: bigint) | Group By Operator [GBY_11] | aggregations:["count(_col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_9] | outputColumnNames:["_col0"] | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_8] | alias:s1 | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 8 [CONTAINS] Reduce Output Operator [RS_27] key expressions:_col0 (type: string) sort order:+ Select Operator [SEL_24] outputColumnNames:["_col0"] Group By Operator [GBY_23] | aggregations:["count(VALUE._col0)"] | outputColumnNames:["_col0"] |<-Map 7 [SIMPLE_EDGE] Reduce Output Operator [RS_22] sort order: Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: bigint) Group By Operator [GBY_21] aggregations:["count(_col0)"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_19] outputColumnNames:["_col0"] Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_18] alias:s1 Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select unionsrc.key, count(1) FROM (select 'max' as key, max(c_int) as value from cbo_t3 s1 UNION ALL select 'min' as key, min(c_int) as value from cbo_t3 s2 UNION ALL select 'avg' as key, avg(c_int) as value from cbo_t3 s3) unionsrc group by unionsrc.key order by unionsrc.key PREHOOK: type: QUERY POSTHOOK: query: explain select unionsrc.key, count(1) FROM (select 'max' as key, max(c_int) as value from cbo_t3 s1 UNION ALL select 'min' as key, min(c_int) as value from cbo_t3 s2 UNION ALL select 'avg' as key, avg(c_int) as value from cbo_t3 s3) unionsrc group by unionsrc.key order by unionsrc.key POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Union 3 (CONTAINS) Reducer 5 <- Reducer 4 (SIMPLE_EDGE) Reducer 4 <- Union 3 (SIMPLE_EDGE) Reducer 7 <- Map 6 (SIMPLE_EDGE), Union 3 (CONTAINS) Reducer 9 <- Map 8 (SIMPLE_EDGE), Union 3 (CONTAINS) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 5 File Output Operator [FS_34] compressed:false Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_33] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 4 [SIMPLE_EDGE] Reduce Output Operator [RS_32] key expressions:_col0 (type: string) sort order:+ Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: bigint) Group By Operator [GBY_30] | aggregations:["count(VALUE._col0)"] | keys:KEY._col0 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE |<-Union 3 [SIMPLE_EDGE] |<-Reducer 2 [CONTAINS] | Reduce Output Operator [RS_29] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | value expressions:_col1 (type: bigint) | Group By Operator [GBY_28] | aggregations:["count(1)"] | keys:_col0 (type: string) | outputColumnNames:["_col0","_col1"] | Select Operator [SEL_6] | outputColumnNames:["_col0"] | Group By Operator [GBY_5] | | aggregations:["count(VALUE._col0)"] | | outputColumnNames:["_col0"] | |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_4] | sort order: | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col0 (type: bigint) | Group By Operator [GBY_3] | aggregations:["count(_col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_1] | outputColumnNames:["_col0"] | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:s1 | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 7 [CONTAINS] | Reduce Output Operator [RS_29] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | value expressions:_col1 (type: bigint) | Group By Operator [GBY_28] | aggregations:["count(1)"] | keys:_col0 (type: string) | outputColumnNames:["_col0","_col1"] | Select Operator [SEL_14] | outputColumnNames:["_col0"] | Group By Operator [GBY_13] | | aggregations:["count(VALUE._col0)"] | | outputColumnNames:["_col0"] | |<-Map 6 [SIMPLE_EDGE] | Reduce Output Operator [RS_12] | sort order: | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col0 (type: bigint) | Group By Operator [GBY_11] | aggregations:["count(_col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_9] | outputColumnNames:["_col0"] | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_8] | alias:s1 | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 9 [CONTAINS] Reduce Output Operator [RS_29] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ value expressions:_col1 (type: bigint) Group By Operator [GBY_28] aggregations:["count(1)"] keys:_col0 (type: string) outputColumnNames:["_col0","_col1"] Select Operator [SEL_24] outputColumnNames:["_col0"] Group By Operator [GBY_23] | aggregations:["count(VALUE._col0)"] | outputColumnNames:["_col0"] |<-Map 8 [SIMPLE_EDGE] Reduce Output Operator [RS_22] sort order: Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: bigint) Group By Operator [GBY_21] aggregations:["count(_col0)"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_19] outputColumnNames:["_col0"] Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_18] alias:s1 Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select cbo_t1.key from cbo_t1 join cbo_t3 where cbo_t1.key=cbo_t3.key and cbo_t1.key >= 1 PREHOOK: type: QUERY POSTHOOK: query: explain select cbo_t1.key from cbo_t1 join cbo_t3 where cbo_t1.key=cbo_t3.key and cbo_t1.key >= 1 POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_12] compressed:false Statistics:Num rows: 18 Data size: 1530 Basic stats: COMPLETE Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Merge Join Operator [MERGEJOIN_17] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} | outputColumnNames:["_col0"] | Statistics:Num rows: 18 Data size: 1530 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_7] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 6 Data size: 425 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_2] | outputColumnNames:["_col0"] | Statistics:Num rows: 6 Data size: 425 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_15] | predicate:(UDFToDouble(key) >= 1.0) (type: boolean) | Statistics:Num rows: 6 Data size: 425 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:cbo_t1 | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 3 [SIMPLE_EDGE] Reduce Output Operator [RS_9] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 6 Data size: 425 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_5] outputColumnNames:["_col0"] Statistics:Num rows: 6 Data size: 425 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator [FIL_16] predicate:(UDFToDouble(key) >= 1.0) (type: boolean) Statistics:Num rows: 6 Data size: 425 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_3] alias:cbo_t3 Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select cbo_t1.c_int, cbo_t2.c_int from cbo_t1 left outer join cbo_t2 on cbo_t1.key=cbo_t2.key PREHOOK: type: QUERY POSTHOOK: query: explain select cbo_t1.c_int, cbo_t2.c_int from cbo_t1 left outer join cbo_t2 on cbo_t1.key=cbo_t2.key POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_8] compressed:false Statistics:Num rows: 100 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_7] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 100 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator [MERGEJOIN_11] | condition map:[{"":"Left Outer Join0 to 1"}] | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} | outputColumnNames:["_col1","_col3"] | Statistics:Num rows: 100 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_4] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col1 (type: int) | Select Operator [SEL_1] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:cbo_t1 | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 3 [SIMPLE_EDGE] Reduce Output Operator [RS_5] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: int) Select Operator [SEL_3] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_2] alias:cbo_t2 Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select cbo_t1.c_int, cbo_t2.c_int from cbo_t1 full outer join cbo_t2 on cbo_t1.key=cbo_t2.key PREHOOK: type: QUERY POSTHOOK: query: explain select cbo_t1.c_int, cbo_t2.c_int from cbo_t1 full outer join cbo_t2 on cbo_t1.key=cbo_t2.key POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_8] compressed:false Statistics:Num rows: 100 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_7] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 100 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator [MERGEJOIN_9] | condition map:[{"":"Outer Join 0 to 1"}] | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} | outputColumnNames:["_col1","_col3"] | Statistics:Num rows: 100 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_4] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col1 (type: int) | Select Operator [SEL_1] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:cbo_t1 | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 3 [SIMPLE_EDGE] Reduce Output Operator [RS_5] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: int) Select Operator [SEL_3] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_2] alias:cbo_t2 Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select b, cbo_t1.c, cbo_t2.p, q, cbo_t3.c_int from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1) cbo_t1 join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2) cbo_t2 on cbo_t1.a=p join cbo_t3 on cbo_t1.a=key PREHOOK: type: QUERY POSTHOOK: query: explain select b, cbo_t1.c, cbo_t2.p, q, cbo_t3.c_int from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1) cbo_t1 join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2) cbo_t2 on cbo_t1.a=p join cbo_t3 on cbo_t1.a=key POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_14] compressed:false Statistics:Num rows: 291 Data size: 29391 Basic stats: COMPLETE Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_13] outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] Statistics:Num rows: 291 Data size: 29391 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator [MERGEJOIN_24] | condition map:[{"":"Inner Join 0 to 1"},{"":"Inner Join 0 to 2"}] | keys:{"2":"_col0 (type: string)","1":"_col0 (type: string)","0":"_col0 (type: string)"} | outputColumnNames:["_col1","_col2","_col4","_col5","_col6"] | Statistics:Num rows: 291 Data size: 29391 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_7] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 18 Data size: 1488 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col1 (type: int), _col2 (type: float) | Select Operator [SEL_1] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 18 Data size: 1488 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_21] | predicate:key is not null (type: boolean) | Statistics:Num rows: 18 Data size: 1488 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:cbo_t1 | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 3 [SIMPLE_EDGE] | Reduce Output Operator [RS_9] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col1 (type: int) | Select Operator [SEL_3] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_22] | predicate:key is not null (type: boolean) | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_2] | alias:cbo_t3 | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 4 [SIMPLE_EDGE] Reduce Output Operator [RS_11] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: int) Select Operator [SEL_5] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator [FIL_23] predicate:key is not null (type: boolean) Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_4] alias:cbo_t2 Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select key, cbo_t1.c_int, cbo_t2.p, q from cbo_t1 join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2) cbo_t2 on cbo_t1.key=p join (select key as a, c_int as b, cbo_t3.c_float as c from cbo_t3)cbo_t3 on cbo_t1.key=a PREHOOK: type: QUERY POSTHOOK: query: explain select key, cbo_t1.c_int, cbo_t2.p, q from cbo_t1 join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2) cbo_t2 on cbo_t1.key=p join (select key as a, c_int as b, cbo_t3.c_float as c from cbo_t3)cbo_t3 on cbo_t1.key=a POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_14] compressed:false Statistics:Num rows: 291 Data size: 51798 Basic stats: COMPLETE Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_13] outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 291 Data size: 51798 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator [MERGEJOIN_24] | condition map:[{"":"Inner Join 0 to 1"},{"":"Inner Join 0 to 2"}] | keys:{"2":"_col0 (type: string)","1":"_col0 (type: string)","0":"_col0 (type: string)"} | outputColumnNames:["_col0","_col1","_col3","_col4"] | Statistics:Num rows: 291 Data size: 51798 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_7] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col1 (type: int) | Select Operator [SEL_1] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_21] | predicate:key is not null (type: boolean) | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:cbo_t1 | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 3 [SIMPLE_EDGE] | Reduce Output Operator [RS_9] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 18 Data size: 1360 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_3] | outputColumnNames:["_col0"] | Statistics:Num rows: 18 Data size: 1360 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_22] | predicate:key is not null (type: boolean) | Statistics:Num rows: 18 Data size: 1360 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_2] | alias:cbo_t3 | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 4 [SIMPLE_EDGE] Reduce Output Operator [RS_11] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: int) Select Operator [SEL_5] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator [FIL_23] predicate:key is not null (type: boolean) Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_4] alias:cbo_t2 Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select * from (select q, b, cbo_t2.p, cbo_t1.c, cbo_t3.c_int from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 full outer join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q == 2) and (b > 0 or c_int >= 0)) R where (q + 1 = 2) and (R.b > 0 or c_int >= 0) PREHOOK: type: QUERY POSTHOOK: query: explain select * from (select q, b, cbo_t2.p, cbo_t1.c, cbo_t3.c_int from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 full outer join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q == 2) and (b > 0 or c_int >= 0)) R where (q + 1 = 2) and (R.b > 0 or c_int >= 0) POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) Reducer 3 <- Map 5 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 3 File Output Operator [FS_20] compressed:false Statistics:Num rows: 8 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_19] outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] Statistics:Num rows: 8 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator [FIL_18] predicate:((_col1 > 0) or (_col6 >= 0)) (type: boolean) Statistics:Num rows: 8 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator [MERGEJOIN_29] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} | outputColumnNames:["_col1","_col2","_col3","_col4","_col6"] | Statistics:Num rows: 14 Data size: 168 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 5 [SIMPLE_EDGE] | Reduce Output Operator [RS_16] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col1 (type: int) | Select Operator [SEL_12] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_27] | predicate:key is not null (type: boolean) | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_11] | alias:cbo_t3 | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_14] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 4 Data size: 728 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: int), _col2 (type: float), _col3 (type: string), _col4 (type: int) Filter Operator [FIL_24] predicate:((((_col1 + _col4) = 2) and ((_col4 + 1) = 2)) and _col0 is not null) (type: boolean) Statistics:Num rows: 4 Data size: 728 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator [MERGEJOIN_28] | condition map:[{"":"Outer Join 0 to 1"}] | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] | Statistics:Num rows: 18 Data size: 3276 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_6] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col1 (type: int), _col2 (type: float) | Select Operator [SEL_2] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_25] | predicate:(((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) (type: boolean) | Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:cbo_t1 | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 4 [SIMPLE_EDGE] Reduce Output Operator [RS_7] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 6 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: int) Select Operator [SEL_5] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 6 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator [FIL_26] predicate:(((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) (type: boolean) Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_3] alias:cbo_t2 Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select * from (select q, b, cbo_t2.p, cbo_t1.c, cbo_t3.c_int from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 right outer join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p right outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q == 2) and (b > 0 or c_int >= 0)) R where (q + 1 = 2) and (R.b > 0 or c_int >= 0) PREHOOK: type: QUERY POSTHOOK: query: explain select * from (select q, b, cbo_t2.p, cbo_t1.c, cbo_t3.c_int from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 right outer join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p right outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q == 2) and (b > 0 or c_int >= 0)) R where (q + 1 = 2) and (R.b > 0 or c_int >= 0) POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_14] compressed:false Statistics:Num rows: 12 Data size: 1212 Basic stats: COMPLETE Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_13] outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] Statistics:Num rows: 12 Data size: 1212 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator [FIL_17] predicate:((((_col1 + _col4) = 2) and ((_col1 > 0) or (_col6 >= 0))) and ((_col4 + 1) = 2)) (type: boolean) Statistics:Num rows: 12 Data size: 1212 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator [MERGEJOIN_20] | condition map:[{"":"Right Outer Join0 to 1"},{"":"Right Outer Join0 to 2"}] | keys:{"2":"_col0 (type: string)","1":"_col0 (type: string)","0":"_col0 (type: string)"} | outputColumnNames:["_col1","_col2","_col3","_col4","_col6"] | Statistics:Num rows: 72 Data size: 7272 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_8] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col1 (type: int), _col2 (type: float) | Select Operator [SEL_2] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_18] | predicate:(((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) (type: boolean) | Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:cbo_t1 | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 3 [SIMPLE_EDGE] | Reduce Output Operator [RS_9] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 6 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col1 (type: int) | Select Operator [SEL_5] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 6 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_19] | predicate:(((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) (type: boolean) | Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_3] | alias:cbo_t2 | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 4 [SIMPLE_EDGE] Reduce Output Operator [RS_10] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: int) Select Operator [SEL_7] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_6] alias:cbo_t3 Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select key, (c_int+1)+2 as x, sum(c_int) from cbo_t1 group by c_float, cbo_t1.c_int, key order by x limit 1 PREHOOK: type: QUERY POSTHOOK: query: explain select key, (c_int+1)+2 as x, sum(c_int) from cbo_t1 group by c_float, cbo_t1.c_int, key order by x limit 1 POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:1 Stage-1 Reducer 3 File Output Operator [FS_10] compressed:false Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Limit [LIM_9] Number of rows:1 Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_8] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 10 Data size: 885 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_7] key expressions:_col1 (type: int) sort order:+ Statistics:Num rows: 10 Data size: 885 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: string), _col2 (type: bigint) Select Operator [SEL_6] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 10 Data size: 885 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator [GBY_5] | aggregations:["sum(VALUE._col0)"] | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_4] key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) sort order:+++ Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col3 (type: bigint) Group By Operator [GBY_3] aggregations:["sum(_col1)"] keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_1] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_0] alias:cbo_t1 Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select x, y, count(*) from (select key, (c_int+c_float+1+2) as x, sum(c_int) as y from cbo_t1 group by c_float, cbo_t1.c_int, key) R group by y, x order by x,y limit 1 PREHOOK: type: QUERY POSTHOOK: query: explain select x, y, count(*) from (select key, (c_int+c_float+1+2) as x, sum(c_int) as y from cbo_t1 group by c_float, cbo_t1.c_int, key) R group by y, x order by x,y limit 1 POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:1 Stage-1 Reducer 4 File Output Operator [FS_15] compressed:false Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Limit [LIM_14] Number of rows:1 Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_13] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 5 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 3 [SIMPLE_EDGE] Reduce Output Operator [RS_12] key expressions:_col0 (type: float), _col1 (type: bigint) sort order:++ Statistics:Num rows: 5 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col2 (type: bigint) Select Operator [SEL_11] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 5 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator [GBY_10] | aggregations:["count(VALUE._col0)"] | keys:KEY._col0 (type: bigint), KEY._col1 (type: float) | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 5 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_9] key expressions:_col0 (type: bigint), _col1 (type: float) Map-reduce partition columns:_col0 (type: bigint), _col1 (type: float) sort order:++ Statistics:Num rows: 5 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col2 (type: bigint) Group By Operator [GBY_8] aggregations:["count()"] keys:_col0 (type: bigint), _col1 (type: float) outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 5 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_6] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator [GBY_5] | aggregations:["sum(VALUE._col0)"] | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_4] key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) sort order:+++ Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col3 (type: bigint) Group By Operator [GBY_3] aggregations:["sum(_col1)"] keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_1] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_0] alias:cbo_t1 Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select key from(select key from (select key from cbo_t1 limit 5)cbo_t2 limit 5)cbo_t3 limit 5 PREHOOK: type: QUERY POSTHOOK: query: explain select key from(select key from (select key from cbo_t1 limit 5)cbo_t2 limit 5)cbo_t3 limit 5 POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:5 Stage-1 Reducer 3 File Output Operator [FS_13] compressed:false Statistics:Num rows: 5 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Limit [LIM_12] Number of rows:5 Statistics:Num rows: 5 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE Limit [LIM_10] Number of rows:5 Statistics:Num rows: 5 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_9] | outputColumnNames:["_col0"] | Statistics:Num rows: 5 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_8] sort order: Statistics:Num rows: 5 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: string) Limit [LIM_7] Number of rows:5 Statistics:Num rows: 5 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE Limit [LIM_5] Number of rows:5 Statistics:Num rows: 5 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_4] | outputColumnNames:["_col0"] | Statistics:Num rows: 5 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_3] sort order: Statistics:Num rows: 5 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: string) Limit [LIM_2] Number of rows:5 Statistics:Num rows: 5 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_1] outputColumnNames:["_col0"] Statistics:Num rows: 20 Data size: 1530 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_0] alias:cbo_t1 Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select key, c_int from(select key, c_int from (select key, c_int from cbo_t1 order by c_int limit 5)cbo_t1 order by c_int limit 5)cbo_t2 order by c_int limit 5 PREHOOK: type: QUERY POSTHOOK: query: explain select key, c_int from(select key, c_int from (select key, c_int from cbo_t1 order by c_int limit 5)cbo_t1 order by c_int limit 5)cbo_t2 order by c_int limit 5 POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:5 Stage-1 Reducer 4 File Output Operator [FS_13] compressed:false Statistics:Num rows: 5 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Limit [LIM_12] Number of rows:5 Statistics:Num rows: 5 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator [SEL_11] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 5 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE |<-Reducer 3 [SIMPLE_EDGE] Reduce Output Operator [RS_10] key expressions:_col1 (type: int) sort order:+ Statistics:Num rows: 5 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE value expressions:_col0 (type: string) Limit [LIM_8] Number of rows:5 Statistics:Num rows: 5 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator [SEL_7] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 5 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_6] key expressions:_col1 (type: int) sort order:+ Statistics:Num rows: 5 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: string) Limit [LIM_4] Number of rows:5 Statistics:Num rows: 5 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_3] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_2] key expressions:_col1 (type: int) sort order:+ Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: string) Select Operator [SEL_1] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_0] alias:cbo_t1 Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key order by a limit 5) cbo_t1 join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key order by q/10 desc, r asc limit 5) cbo_t2 on cbo_t1.a=p join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 0) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c order by cbo_t3.c_int+c desc, c limit 5 PREHOOK: type: QUERY POSTHOOK: query: explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key order by a limit 5) cbo_t1 join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key order by q/10 desc, r asc limit 5) cbo_t2 on cbo_t1.a=p join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 0) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c order by cbo_t3.c_int+c desc, c limit 5 POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Reducer 11 <- Reducer 10 (SIMPLE_EDGE) Reducer 10 <- Map 9 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE) Reducer 7 <- Reducer 6 (SIMPLE_EDGE) Reducer 6 <- Map 5 (SIMPLE_EDGE) Reducer 8 <- Reducer 11 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:5 Stage-1 Reducer 4 File Output Operator [FS_50] compressed:false Statistics:Num rows: 5 Data size: 410 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Limit [LIM_49] Number of rows:5 Statistics:Num rows: 5 Data size: 410 Basic stats: COMPLETE Column stats: NONE Select Operator [SEL_48] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 6 Data size: 494 Basic stats: COMPLETE Column stats: NONE |<-Reducer 3 [SIMPLE_EDGE] Reduce Output Operator [RS_47] key expressions:(UDFToLong(_col0) + _col1) (type: bigint), _col1 (type: bigint) sort order:-+ Statistics:Num rows: 6 Data size: 494 Basic stats: COMPLETE Column stats: NONE value expressions:_col0 (type: int), _col2 (type: bigint) Group By Operator [GBY_45] | aggregations:["count(VALUE._col0)"] | keys:KEY._col0 (type: int), KEY._col1 (type: bigint) | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 6 Data size: 494 Basic stats: COMPLETE Column stats: NONE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_44] key expressions:_col0 (type: int), _col1 (type: bigint) Map-reduce partition columns:_col0 (type: int), _col1 (type: bigint) sort order:++ Statistics:Num rows: 12 Data size: 989 Basic stats: COMPLETE Column stats: NONE value expressions:_col2 (type: bigint) Group By Operator [GBY_43] aggregations:["count()"] keys:_col0 (type: int), _col1 (type: bigint) outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 12 Data size: 989 Basic stats: COMPLETE Column stats: NONE Select Operator [SEL_39] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 12 Data size: 989 Basic stats: COMPLETE Column stats: NONE Filter Operator [FIL_56] predicate:((_col3 > 0) or (_col1 >= 0)) (type: boolean) Statistics:Num rows: 12 Data size: 989 Basic stats: COMPLETE Column stats: NONE Merge Join Operator [MERGEJOIN_64] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} | outputColumnNames:["_col1","_col3","_col4"] | Statistics:Num rows: 19 Data size: 1566 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_35] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col1 (type: int) | Select Operator [SEL_1] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_57] | predicate:key is not null (type: boolean) | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:cbo_t3 | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 8 [SIMPLE_EDGE] Reduce Output Operator [RS_37] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE value expressions:_col1 (type: int), _col2 (type: bigint) Select Operator [SEL_31] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE Filter Operator [FIL_58] predicate:((_col3 + _col1) >= 0) (type: boolean) Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE Merge Join Operator [MERGEJOIN_63] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} | outputColumnNames:["_col1","_col2","_col3","_col4"] | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 11 [SIMPLE_EDGE] | Reduce Output Operator [RS_29] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col1 (type: int), _col2 (type: bigint) | Filter Operator [FIL_61] | predicate:_col0 is not null (type: boolean) | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE | Limit [LIM_24] | Number of rows:5 | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_23] | | outputColumnNames:["_col0","_col1","_col2"] | | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE | |<-Reducer 10 [SIMPLE_EDGE] | Reduce Output Operator [RS_22] | key expressions:_col0 (type: string) | sort order:+ | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col1 (type: int), _col2 (type: bigint) | Select Operator [SEL_21] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE | Group By Operator [GBY_20] | | aggregations:["sum(VALUE._col0)"] | | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) | | outputColumnNames:["_col0","_col1","_col2","_col3"] | | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE | |<-Map 9 [SIMPLE_EDGE] | Reduce Output Operator [RS_19] | key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) | Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) | sort order:+++ | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col3 (type: bigint) | Group By Operator [GBY_18] | aggregations:["sum(_col1)"] | keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_16] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_62] | predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) (type: boolean) | Statistics:Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_14] | alias:cbo_t1 | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 7 [SIMPLE_EDGE] Reduce Output Operator [RS_27] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: int) Filter Operator [FIL_59] predicate:_col0 is not null (type: boolean) Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE Limit [LIM_12] Number of rows:5 Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_11] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 6 [SIMPLE_EDGE] Reduce Output Operator [RS_10] key expressions:_col3 (type: double), _col2 (type: bigint) sort order:-+ Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: string), _col1 (type: int) Select Operator [SEL_9] outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator [GBY_8] | aggregations:["sum(VALUE._col0)"] | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 5 [SIMPLE_EDGE] Reduce Output Operator [RS_7] key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) sort order:+++ Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col3 (type: bigint) Group By Operator [GBY_6] aggregations:["sum(_col1)"] keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_4] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator [FIL_60] predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) (type: boolean) Statistics:Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_2] alias:cbo_t2 Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select cbo_t1.c_int from cbo_t1 left semi join cbo_t2 on cbo_t1.key=cbo_t2.key where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) PREHOOK: type: QUERY POSTHOOK: query: explain select cbo_t1.c_int from cbo_t1 left semi join cbo_t2 on cbo_t1.key=cbo_t2.key where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_13] compressed:false Statistics:Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_12] outputColumnNames:["_col0"] Statistics:Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator [MERGEJOIN_18] | condition map:[{"":"Left Semi Join 0 to 1"}] | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} | outputColumnNames:["_col1"] | Statistics:Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_8] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 5 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col1 (type: int) | Select Operator [SEL_2] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 5 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_16] | predicate:((((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) and key is not null) (type: boolean) | Statistics:Num rows: 5 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:cbo_t1 | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 3 [SIMPLE_EDGE] Reduce Output Operator [RS_10] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 5 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator [GBY_6] keys:_col0 (type: string) outputColumnNames:["_col0"] Statistics:Num rows: 5 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_4] outputColumnNames:["_col0"] Statistics:Num rows: 18 Data size: 1360 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator [FIL_17] predicate:key is not null (type: boolean) Statistics:Num rows: 18 Data size: 1360 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_3] alias:cbo_t2 Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select * from (select c, b, a from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 left semi join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p left semi join cbo_t3 on cbo_t1.a=key where (b + 1 == 2) and (b > 0 or c >= 0)) R where (b + 1 = 2) and (R.b > 0 or c >= 0) PREHOOK: type: QUERY POSTHOOK: query: explain select * from (select c, b, a from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 left semi join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p left semi join cbo_t3 on cbo_t1.a=key where (b + 1 == 2) and (b > 0 or c >= 0)) R where (b + 1 = 2) and (R.b > 0 or c >= 0) POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_20] compressed:false Statistics:Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_19] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator [MERGEJOIN_30] | condition map:[{"":"Left Semi Join 0 to 1"},{"":"Left Semi Join 0 to 2"}] | keys:{"2":"_col0 (type: string)","1":"_col0 (type: string)","0":"_col0 (type: string)"} | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_13] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 5 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col1 (type: int), _col2 (type: float) | Select Operator [SEL_2] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 5 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_27] | predicate:((((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) and key is not null) (type: boolean) | Statistics:Num rows: 5 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:cbo_t1 | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 3 [SIMPLE_EDGE] | Reduce Output Operator [RS_15] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE | Group By Operator [GBY_9] | keys:_col0 (type: string) | outputColumnNames:["_col0"] | Statistics:Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_5] | outputColumnNames:["_col0"] | Statistics:Num rows: 5 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_28] | predicate:((((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) and key is not null) (type: boolean) | Statistics:Num rows: 5 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_3] | alias:cbo_t2 | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 4 [SIMPLE_EDGE] Reduce Output Operator [RS_17] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 6 Data size: 425 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator [GBY_11] keys:_col0 (type: string) outputColumnNames:["_col0"] Statistics:Num rows: 6 Data size: 425 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_7] outputColumnNames:["_col0"] Statistics:Num rows: 18 Data size: 1360 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator [FIL_29] predicate:key is not null (type: boolean) Statistics:Num rows: 18 Data size: 1360 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_6] alias:cbo_t3 Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select a, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by a+b desc, c asc) cbo_t1 left semi join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by q+r/10 desc, p) cbo_t2 on cbo_t1.a=p left semi join cbo_t3 on cbo_t1.a=key where (b + 1 >= 0) and (b > 0 or a >= 0) group by a, c having a > 0 and (a >=1 or c >= 1) and (a + c) >= 0 order by c, a PREHOOK: type: QUERY POSTHOOK: query: explain select a, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by a+b desc, c asc) cbo_t1 left semi join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by q+r/10 desc, p) cbo_t2 on cbo_t1.a=p left semi join cbo_t3 on cbo_t1.a=key where (b + 1 >= 0) and (b > 0 or a >= 0) group by a, c having a > 0 and (a >=1 or c >= 1) and (a + c) >= 0 order by c, a POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Reducer 5 <- Reducer 4 (SIMPLE_EDGE) Reducer 4 <- Map 10 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) Reducer 6 <- Reducer 5 (SIMPLE_EDGE) Reducer 9 <- Reducer 8 (SIMPLE_EDGE) Reducer 8 <- Map 7 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 6 File Output Operator [FS_44] compressed:false Statistics:Num rows: 6 Data size: 431 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_43] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 6 Data size: 431 Basic stats: COMPLETE Column stats: NONE |<-Reducer 5 [SIMPLE_EDGE] Reduce Output Operator [RS_42] key expressions:_col1 (type: bigint), _col0 (type: string) sort order:++ Statistics:Num rows: 6 Data size: 431 Basic stats: COMPLETE Column stats: NONE value expressions:_col2 (type: bigint) Group By Operator [GBY_40] | aggregations:["count(VALUE._col0)"] | keys:KEY._col0 (type: string), KEY._col1 (type: bigint) | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 6 Data size: 431 Basic stats: COMPLETE Column stats: NONE |<-Reducer 4 [SIMPLE_EDGE] Reduce Output Operator [RS_39] key expressions:_col0 (type: string), _col1 (type: bigint) Map-reduce partition columns:_col0 (type: string), _col1 (type: bigint) sort order:++ Statistics:Num rows: 13 Data size: 935 Basic stats: COMPLETE Column stats: NONE value expressions:_col2 (type: bigint) Group By Operator [GBY_38] aggregations:["count()"] keys:_col0 (type: string), _col1 (type: bigint) outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 13 Data size: 935 Basic stats: COMPLETE Column stats: NONE Merge Join Operator [MERGEJOIN_56] | condition map:[{"":"Left Semi Join 0 to 1"},{"":"Left Semi Join 0 to 2"}] | keys:{"2":"_col0 (type: string)","1":"_col0 (type: string)","0":"_col0 (type: string)"} | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 13 Data size: 935 Basic stats: COMPLETE Column stats: NONE |<-Map 10 [SIMPLE_EDGE] | Reduce Output Operator [RS_35] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 6 Data size: 425 Basic stats: COMPLETE Column stats: COMPLETE | Group By Operator [GBY_29] | keys:_col0 (type: string) | outputColumnNames:["_col0"] | Statistics:Num rows: 6 Data size: 425 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_25] | outputColumnNames:["_col0"] | Statistics:Num rows: 18 Data size: 1360 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_55] | predicate:key is not null (type: boolean) | Statistics:Num rows: 18 Data size: 1360 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_24] | alias:cbo_t3 | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 3 [SIMPLE_EDGE] | Reduce Output Operator [RS_31] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE | value expressions:_col1 (type: bigint) | Select Operator [SEL_9] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE | |<-Reducer 2 [SIMPLE_EDGE] | Reduce Output Operator [RS_8] | key expressions:_col3 (type: double), _col2 (type: bigint) | sort order:-+ | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE | value expressions:_col0 (type: string) | Filter Operator [FIL_51] | predicate:(((_col1 + 1) >= 0) and ((_col1 > 0) or (UDFToDouble(_col0) >= 0.0))) (type: boolean) | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE | Select Operator [SEL_7] | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE | Filter Operator [FIL_52] | predicate:(((UDFToDouble(_col2) + UDFToDouble(_col3)) >= 0.0) and ((UDFToDouble(_col2) >= 1.0) or (_col3 >= 1))) (type: boolean) | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE | Group By Operator [GBY_6] | | aggregations:["sum(VALUE._col0)"] | | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) | | outputColumnNames:["_col0","_col1","_col2","_col3"] | | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE | |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_5] | key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) | Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) | sort order:+++ | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE | value expressions:_col3 (type: bigint) | Group By Operator [GBY_4] | aggregations:["sum(_col1)"] | keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE | Select Operator [SEL_2] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE | Filter Operator [FIL_53] | predicate:((((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) and (UDFToDouble(key) > 0.0)) and key is not null) (type: boolean) | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE | TableScan [TS_0] | alias:cbo_t1 | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 9 [SIMPLE_EDGE] Reduce Output Operator [RS_33] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE Group By Operator [GBY_27] keys:_col0 (type: string) outputColumnNames:["_col0"] Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE Select Operator [SEL_22] | outputColumnNames:["_col0"] | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE |<-Reducer 8 [SIMPLE_EDGE] Reduce Output Operator [RS_21] key expressions:_col1 (type: double), _col0 (type: string) sort order:-+ Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE Select Operator [SEL_20] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE Group By Operator [GBY_19] | aggregations:["sum(VALUE._col0)"] | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE |<-Map 7 [SIMPLE_EDGE] Reduce Output Operator [RS_18] key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) sort order:+++ Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE value expressions:_col3 (type: bigint) Group By Operator [GBY_17] aggregations:["sum(_col1)"] keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE Select Operator [SEL_15] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE Filter Operator [FIL_54] predicate:(((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) and key is not null) (type: boolean) Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE TableScan [TS_13] alias:cbo_t2 Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select cbo_t1.key as x, c_int as c_int, (((c_int+c_float)*10)+5) as y from cbo_t1 PREHOOK: type: QUERY POSTHOOK: query: explain select cbo_t1.key as x, c_int as c_int, (((c_int+c_float)*10)+5) as y from cbo_t1 POSTHOOK: type: QUERY Plan optimized by CBO. Stage-0 Fetch Operator limit:-1 Select Operator [SEL_1] outputColumnNames:["_col0","_col1","_col2"] TableScan [TS_0] alias:cbo_t1 PREHOOK: query: explain select null from cbo_t1 PREHOOK: type: QUERY POSTHOOK: query: explain select null from cbo_t1 POSTHOOK: type: QUERY Plan optimized by CBO. Stage-0 Fetch Operator limit:-1 Select Operator [SEL_1] outputColumnNames:["_col0"] TableScan [TS_0] alias:cbo_t1 PREHOOK: query: explain select key from cbo_t1 where c_int = -6 or c_int = +6 PREHOOK: type: QUERY POSTHOOK: query: explain select key from cbo_t1 where c_int = -6 or c_int = +6 POSTHOOK: type: QUERY Plan optimized by CBO. Stage-0 Fetch Operator limit:-1 Select Operator [SEL_2] outputColumnNames:["_col0"] Filter Operator [FIL_4] predicate:((c_int = -6) or (c_int = 6)) (type: boolean) TableScan [TS_0] alias:cbo_t1 PREHOOK: query: explain select count(cbo_t1.dt) from cbo_t1 join cbo_t2 on cbo_t1.dt = cbo_t2.dt where cbo_t1.dt = '2014' PREHOOK: type: QUERY POSTHOOK: query: explain select count(cbo_t1.dt) from cbo_t1 join cbo_t2 on cbo_t1.dt = cbo_t2.dt where cbo_t1.dt = '2014' POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 3 File Output Operator [FS_16] compressed:false Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Group By Operator [GBY_14] | aggregations:["count(VALUE._col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_13] sort order: Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions:_col0 (type: bigint) Group By Operator [GBY_12] aggregations:["count(_col0)"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator [SEL_10] outputColumnNames:["_col0"] Statistics:Num rows: 22 Data size: 0 Basic stats: PARTIAL Column stats: NONE Merge Join Operator [MERGEJOIN_20] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{} | Statistics:Num rows: 22 Data size: 0 Basic stats: PARTIAL Column stats: NONE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_7] | sort order: | Statistics:Num rows: 20 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE | Select Operator [SEL_2] | Statistics:Num rows: 20 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE | TableScan [TS_0] | alias:cbo_t1 | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 4 [SIMPLE_EDGE] Reduce Output Operator [RS_8] sort order: Statistics:Num rows: 20 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator [SEL_5] Statistics:Num rows: 20 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE TableScan [TS_3] alias:cbo_t2 Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select * from src_cbo b where not exists (select distinct a.key from src_cbo a where b.value = a.value and a.value > 'val_2' ) PREHOOK: type: QUERY POSTHOOK: query: explain select * from src_cbo b where not exists (select distinct a.key from src_cbo a where b.value = a.value and a.value > 'val_2' ) POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) Reducer 4 <- Map 3 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_16] compressed:false Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_15] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE Filter Operator [FIL_18] predicate:_col2 is null (type: boolean) Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE Merge Join Operator [MERGEJOIN_20] | condition map:[{"":"Left Outer Join0 to 1"}] | keys:{"1":"_col0 (type: string)","0":"_col1 (type: string)"} | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 193 Data size: 51917 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_11] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col0 (type: string) | Select Operator [SEL_2] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:b | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 4 [SIMPLE_EDGE] Reduce Output Operator [RS_12] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 83 Data size: 7553 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_10] outputColumnNames:["_col0"] Statistics:Num rows: 83 Data size: 7553 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator [GBY_9] | keys:KEY._col0 (type: string), KEY._col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 3 [SIMPLE_EDGE] Reduce Output Operator [RS_8] key expressions:_col0 (type: string), _col1 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string) sort order:++ Statistics:Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator [GBY_7] keys:_col0 (type: string), _col1 (type: string) outputColumnNames:["_col0","_col1"] Statistics:Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_5] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator [FIL_19] predicate:(value > 'val_2') (type: boolean) Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_3] alias:b Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select * from src_cbo b group by key, value having not exists (select a.key from src_cbo a where b.value = a.value and a.key = b.key and a.value > 'val_12' ) PREHOOK: type: QUERY POSTHOOK: query: explain select * from src_cbo b group by key, value having not exists (select a.key from src_cbo a where b.value = a.value and a.key = b.key and a.value > 'val_12' ) POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 3 <- Map 4 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 3 File Output Operator [FS_16] compressed:false Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_15] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE Filter Operator [FIL_18] predicate:_col3 is null (type: boolean) Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE Merge Join Operator [MERGEJOIN_20] | condition map:[{"":"Left Outer Join0 to 1"}] | keys:{"1":"_col0 (type: string), _col1 (type: string)","0":"_col1 (type: string), _col0 (type: string)"} | outputColumnNames:["_col0","_col1","_col3"] | Statistics:Num rows: 8 Data size: 696 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 4 [SIMPLE_EDGE] | Reduce Output Operator [RS_12] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_10] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_19] | predicate:(value > 'val_12') (type: boolean) | Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_8] | alias:b | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_11] key expressions:_col1 (type: string), _col0 (type: string) Map-reduce partition columns:_col1 (type: string), _col0 (type: string) sort order:++ Statistics:Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator [GBY_6] | keys:KEY._col0 (type: string), KEY._col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_5] key expressions:_col0 (type: string), _col1 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string) sort order:++ Statistics:Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator [GBY_4] keys:_col0 (type: string), _col1 (type: string) outputColumnNames:["_col0","_col1"] Statistics:Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_2] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_0] alias:b Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: create view cv1 as select * from src_cbo b where exists (select a.key from src_cbo a where b.value = a.value and a.key = b.key and a.value > 'val_9') PREHOOK: type: CREATEVIEW PREHOOK: Input: default@src_cbo PREHOOK: Output: database:default PREHOOK: Output: default@cv1 POSTHOOK: query: create view cv1 as select * from src_cbo b where exists (select a.key from src_cbo a where b.value = a.value and a.key = b.key and a.value > 'val_9') POSTHOOK: type: CREATEVIEW POSTHOOK: Input: default@src_cbo POSTHOOK: Output: database:default POSTHOOK: Output: default@cv1 PREHOOK: query: explain select * from cv1 PREHOOK: type: QUERY POSTHOOK: query: explain select * from cv1 POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_14] compressed:false Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Merge Join Operator [MERGEJOIN_19] | condition map:[{"":"Left Semi Join 0 to 1"}] | keys:{"1":"_col0 (type: string), _col1 (type: string)","0":"_col1 (type: string), _col0 (type: string)"} | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_9] | key expressions:_col1 (type: string), _col0 (type: string) | Map-reduce partition columns:_col1 (type: string), _col0 (type: string) | sort order:++ | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_2] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_17] | predicate:(value is not null and key is not null) (type: boolean) | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:b | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 3 [SIMPLE_EDGE] Reduce Output Operator [RS_11] key expressions:_col0 (type: string), _col1 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string) sort order:++ Statistics:Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator [GBY_7] keys:_col0 (type: string), _col1 (type: string) outputColumnNames:["_col0","_col1"] Statistics:Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_5] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator [FIL_18] predicate:((value > 'val_9') and key is not null) (type: boolean) Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_3] alias:b Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select * from (select * from src_cbo b where exists (select a.key from src_cbo a where b.value = a.value and a.key = b.key and a.value > 'val_9') ) a PREHOOK: type: QUERY POSTHOOK: query: explain select * from (select * from src_cbo b where exists (select a.key from src_cbo a where b.value = a.value and a.key = b.key and a.value > 'val_9') ) a POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_14] compressed:false Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Merge Join Operator [MERGEJOIN_19] | condition map:[{"":"Left Semi Join 0 to 1"}] | keys:{"1":"_col0 (type: string), _col1 (type: string)","0":"_col1 (type: string), _col0 (type: string)"} | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_9] | key expressions:_col1 (type: string), _col0 (type: string) | Map-reduce partition columns:_col1 (type: string), _col0 (type: string) | sort order:++ | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_2] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_17] | predicate:(value is not null and key is not null) (type: boolean) | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:b | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 3 [SIMPLE_EDGE] Reduce Output Operator [RS_11] key expressions:_col0 (type: string), _col1 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string) sort order:++ Statistics:Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator [GBY_7] keys:_col0 (type: string), _col1 (type: string) outputColumnNames:["_col0","_col1"] Statistics:Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_5] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator [FIL_18] predicate:((value > 'val_9') and key is not null) (type: boolean) Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_3] alias:b Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select * from src_cbo where src_cbo.key in (select key from src_cbo s1 where s1.key > '9') PREHOOK: type: QUERY POSTHOOK: query: explain select * from src_cbo where src_cbo.key in (select key from src_cbo s1 where s1.key > '9') POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_14] compressed:false Statistics:Num rows: 168 Data size: 29904 Basic stats: COMPLETE Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Merge Join Operator [MERGEJOIN_19] | condition map:[{"":"Left Semi Join 0 to 1"}] | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 168 Data size: 29904 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_9] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col1 (type: string) | Select Operator [SEL_2] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_17] | predicate:key is not null (type: boolean) | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:src_cbo | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 3 [SIMPLE_EDGE] Reduce Output Operator [RS_11] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 69 Data size: 6003 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator [GBY_7] keys:_col0 (type: string) outputColumnNames:["_col0"] Statistics:Num rows: 69 Data size: 6003 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_5] outputColumnNames:["_col0"] Statistics:Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator [FIL_18] predicate:(key > '9') (type: boolean) Statistics:Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_3] alias:src_cbo Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select p.p_partkey, li.l_suppkey from (select distinct l_partkey as p_partkey from lineitem) p join lineitem li on p.p_partkey = li.l_partkey where li.l_linenumber = 1 and li.l_orderkey in (select l_orderkey from lineitem where l_shipmode = 'AIR' and l_linenumber = li.l_linenumber) PREHOOK: type: QUERY POSTHOOK: query: explain select p.p_partkey, li.l_suppkey from (select distinct l_partkey as p_partkey from lineitem) p join lineitem li on p.p_partkey = li.l_partkey where li.l_linenumber = 1 and li.l_orderkey in (select l_orderkey from lineitem where l_shipmode = 'AIR' and l_linenumber = li.l_linenumber) POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) Reducer 6 <- Map 5 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 3 File Output Operator [FS_26] compressed:false Statistics:Num rows: 33 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_25] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 33 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator [MERGEJOIN_36] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"1":"_col0 (type: int)","0":"_col1 (type: int)"} | outputColumnNames:["_col1","_col2"] | Statistics:Num rows: 33 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] | Reduce Output Operator [RS_21] | key expressions:_col1 (type: int) | Map-reduce partition columns:_col1 (type: int) | sort order:+ | Statistics:Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col2 (type: int) | Merge Join Operator [MERGEJOIN_35] | | condition map:[{"":"Left Semi Join 0 to 1"}] | | keys:{"1":"_col0 (type: int), _col1 (type: int)","0":"_col0 (type: int), _col3 (type: int)"} | | outputColumnNames:["_col1","_col2"] | | Statistics:Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE | |<-Map 1 [SIMPLE_EDGE] | | Reduce Output Operator [RS_16] | | key expressions:_col0 (type: int), _col3 (type: int) | | Map-reduce partition columns:_col0 (type: int), _col3 (type: int) | | sort order:++ | | Statistics:Num rows: 16 Data size: 256 Basic stats: COMPLETE Column stats: COMPLETE | | value expressions:_col1 (type: int), _col2 (type: int) | | Select Operator [SEL_2] | | outputColumnNames:["_col0","_col1","_col2","_col3"] | | Statistics:Num rows: 16 Data size: 256 Basic stats: COMPLETE Column stats: COMPLETE | | Filter Operator [FIL_32] | | predicate:(((l_linenumber = 1) and l_orderkey is not null) and l_partkey is not null) (type: boolean) | | Statistics:Num rows: 16 Data size: 256 Basic stats: COMPLETE Column stats: COMPLETE | | TableScan [TS_0] | | alias:lineitem | | Statistics:Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: COMPLETE | |<-Map 4 [SIMPLE_EDGE] | Reduce Output Operator [RS_18] | key expressions:_col0 (type: int), _col1 (type: int) | Map-reduce partition columns:_col0 (type: int), _col1 (type: int) | sort order:++ | Statistics:Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE | Group By Operator [GBY_14] | keys:_col0 (type: int), _col1 (type: int) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_5] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 14 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_33] | predicate:(((l_shipmode = 'AIR') and l_orderkey is not null) and l_linenumber is not null) (type: boolean) | Statistics:Num rows: 14 Data size: 1344 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_3] | alias:lineitem | Statistics:Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 6 [SIMPLE_EDGE] Reduce Output Operator [RS_23] key expressions:_col0 (type: int) Map-reduce partition columns:_col0 (type: int) sort order:+ Statistics:Num rows: 50 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator [GBY_11] | keys:KEY._col0 (type: int) | outputColumnNames:["_col0"] | Statistics:Num rows: 50 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 5 [SIMPLE_EDGE] Reduce Output Operator [RS_10] key expressions:_col0 (type: int) Map-reduce partition columns:_col0 (type: int) sort order:+ Statistics:Num rows: 50 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator [GBY_9] keys:_col0 (type: int) outputColumnNames:["_col0"] Statistics:Num rows: 50 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_7] outputColumnNames:["_col0"] Statistics:Num rows: 100 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator [FIL_34] predicate:l_partkey is not null (type: boolean) Statistics:Num rows: 100 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_6] alias:lineitem Statistics:Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select key, value, count(*) from src_cbo b where b.key in (select key from src_cbo where src_cbo.key > '8') group by key, value having count(*) in (select count(*) from src_cbo s1 where s1.key > '9' group by s1.key ) PREHOOK: type: QUERY POSTHOOK: query: explain select key, value, count(*) from src_cbo b where b.key in (select key from src_cbo where src_cbo.key > '8') group by key, value having count(*) in (select count(*) from src_cbo s1 where s1.key > '9' group by s1.key ) POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) Reducer 7 <- Map 6 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 4 File Output Operator [FS_34] compressed:false Statistics:Num rows: 41 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Merge Join Operator [MERGEJOIN_46] | condition map:[{"":"Left Semi Join 0 to 1"}] | keys:{"1":"_col0 (type: bigint)","0":"_col2 (type: bigint)"} | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 41 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE |<-Reducer 3 [SIMPLE_EDGE] | Reduce Output Operator [RS_29] | key expressions:_col2 (type: bigint) | Map-reduce partition columns:_col2 (type: bigint) | sort order:+ | Statistics:Num rows: 84 Data size: 15624 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col0 (type: string), _col1 (type: string) | Filter Operator [FIL_40] | predicate:_col2 is not null (type: boolean) | Statistics:Num rows: 84 Data size: 15624 Basic stats: COMPLETE Column stats: COMPLETE | Group By Operator [GBY_16] | | aggregations:["count(VALUE._col0)"] | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | outputColumnNames:["_col0","_col1","_col2"] | | Statistics:Num rows: 84 Data size: 15624 Basic stats: COMPLETE Column stats: COMPLETE | |<-Reducer 2 [SIMPLE_EDGE] | Reduce Output Operator [RS_15] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Statistics:Num rows: 84 Data size: 15624 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col2 (type: bigint) | Group By Operator [GBY_14] | aggregations:["count()"] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 84 Data size: 15624 Basic stats: COMPLETE Column stats: COMPLETE | Merge Join Operator [MERGEJOIN_45] | | condition map:[{"":"Left Semi Join 0 to 1"}] | | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 168 Data size: 29904 Basic stats: COMPLETE Column stats: COMPLETE | |<-Map 1 [SIMPLE_EDGE] | | Reduce Output Operator [RS_9] | | key expressions:_col0 (type: string) | | Map-reduce partition columns:_col0 (type: string) | | sort order:+ | | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE | | value expressions:_col1 (type: string) | | Select Operator [SEL_2] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE | | Filter Operator [FIL_41] | | predicate:key is not null (type: boolean) | | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE | | TableScan [TS_0] | | alias:b | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE | |<-Map 5 [SIMPLE_EDGE] | Reduce Output Operator [RS_11] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 69 Data size: 6003 Basic stats: COMPLETE Column stats: COMPLETE | Group By Operator [GBY_7] | keys:_col0 (type: string) | outputColumnNames:["_col0"] | Statistics:Num rows: 69 Data size: 6003 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_5] | outputColumnNames:["_col0"] | Statistics:Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_42] | predicate:(key > '8') (type: boolean) | Statistics:Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_3] | alias:b | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 7 [SIMPLE_EDGE] Reduce Output Operator [RS_31] key expressions:_col0 (type: bigint) Map-reduce partition columns:_col0 (type: bigint) sort order:+ Statistics:Num rows: 34 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator [GBY_27] keys:_col0 (type: bigint) outputColumnNames:["_col0"] Statistics:Num rows: 34 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_25] outputColumnNames:["_col0"] Statistics:Num rows: 69 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator [FIL_43] predicate:_col1 is not null (type: boolean) Statistics:Num rows: 69 Data size: 6555 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator [GBY_24] | aggregations:["count(VALUE._col0)"] | keys:KEY._col0 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 69 Data size: 6555 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 6 [SIMPLE_EDGE] Reduce Output Operator [RS_23] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 69 Data size: 6555 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: bigint) Group By Operator [GBY_22] aggregations:["count()"] keys:_col0 (type: string) outputColumnNames:["_col0","_col1"] Statistics:Num rows: 69 Data size: 6555 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_20] outputColumnNames:["_col0"] Statistics:Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator [FIL_44] predicate:(key > '9') (type: boolean) Statistics:Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_18] alias:b Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select p_mfgr, p_name, avg(p_size) from part group by p_mfgr, p_name having p_name in (select first_value(p_name) over(partition by p_mfgr order by p_size) from part) PREHOOK: type: QUERY POSTHOOK: query: explain select p_mfgr, p_name, avg(p_size) from part group by p_mfgr, p_name having p_name in (select first_value(p_name) over(partition by p_mfgr order by p_size) from part) POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) Reducer 5 <- Map 4 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 3 File Output Operator [FS_22] compressed:false Statistics:Num rows: 6 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Merge Join Operator [MERGEJOIN_27] | condition map:[{"":"Left Semi Join 0 to 1"}] | keys:{"1":"_col0 (type: string)","0":"_col1 (type: string)"} | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 6 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] | Reduce Output Operator [RS_17] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ | Statistics:Num rows: 13 Data size: 2951 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col0 (type: string), _col2 (type: double) | Group By Operator [GBY_6] | | aggregations:["avg(VALUE._col0)"] | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | outputColumnNames:["_col0","_col1","_col2"] | | Statistics:Num rows: 13 Data size: 2951 Basic stats: COMPLETE Column stats: COMPLETE | |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_5] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Statistics:Num rows: 13 Data size: 2847 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col2 (type: struct) | Group By Operator [GBY_4] | aggregations:["avg(_col2)"] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 13 Data size: 2847 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_2] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_25] | predicate:p_name is not null (type: boolean) | Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:part | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 5 [SIMPLE_EDGE] Reduce Output Operator [RS_19] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator [GBY_15] keys:_col0 (type: string) outputColumnNames:["_col0"] Statistics:Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_12] outputColumnNames:["_col0"] Statistics:Num rows: 13 Data size: 2392 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator [FIL_26] predicate:first_value_window_0 is not null (type: boolean) Statistics:Num rows: 13 Data size: 2899 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator [PTF_11] Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"_col2","name:":"windowingtablefunction","order by:":"_col5"}] Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_10] | outputColumnNames:["_col1","_col2","_col5"] | Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 4 [SIMPLE_EDGE] Reduce Output Operator [RS_9] key expressions:p_mfgr (type: string), p_size (type: int) Map-reduce partition columns:p_mfgr (type: string) sort order:++ Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE value expressions:p_name (type: string) TableScan [TS_8] alias:part Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select * from src_cbo where src_cbo.key not in ( select key from src_cbo s1 where s1.key > '2' ) order by key PREHOOK: type: QUERY POSTHOOK: query: explain select * from src_cbo where src_cbo.key not in ( select key from src_cbo s1 where s1.key > '2' ) order by key POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) Reducer 3 <- Map 7 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE) Reducer 6 <- Map 5 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 4 File Output Operator [FS_27] compressed:false Statistics:Num rows: 302 Data size: 53756 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_26] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 302 Data size: 53756 Basic stats: COMPLETE Column stats: NONE |<-Reducer 3 [SIMPLE_EDGE] Reduce Output Operator [RS_25] key expressions:_col0 (type: string) sort order:+ Statistics:Num rows: 302 Data size: 53756 Basic stats: COMPLETE Column stats: NONE value expressions:_col1 (type: string) Select Operator [SEL_24] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 302 Data size: 53756 Basic stats: COMPLETE Column stats: NONE Filter Operator [FIL_30] predicate:_col3 is null (type: boolean) Statistics:Num rows: 302 Data size: 53756 Basic stats: COMPLETE Column stats: NONE Merge Join Operator [MERGEJOIN_35] | condition map:[{"":"Left Outer Join0 to 1"}] | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} | outputColumnNames:["_col0","_col1","_col3"] | Statistics:Num rows: 605 Data size: 107690 Basic stats: COMPLETE Column stats: NONE |<-Map 7 [SIMPLE_EDGE] | Reduce Output Operator [RS_21] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_15] | outputColumnNames:["_col0"] | Statistics:Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_33] | predicate:(key > '2') (type: boolean) | Statistics:Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_13] | alias:src_cbo | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_20] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 550 Data size: 97900 Basic stats: COMPLETE Column stats: NONE value expressions:_col1 (type: string) Merge Join Operator [MERGEJOIN_34] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{} | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 550 Data size: 97900 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_17] | sort order: | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col0 (type: string), _col1 (type: string) | Select Operator [SEL_2] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:src_cbo | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 6 [SIMPLE_EDGE] Reduce Output Operator [RS_18] sort order: Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator [SEL_10] Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Filter Operator [FIL_31] predicate:(_col0 = 0) (type: boolean) Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator [GBY_9] | aggregations:["count(VALUE._col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 5 [SIMPLE_EDGE] Reduce Output Operator [RS_8] sort order: Statistics:Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: bigint) Group By Operator [GBY_7] aggregations:["count()"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_5] Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE Filter Operator [FIL_32] predicate:((key > '2') and key is null) (type: boolean) Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE TableScan [TS_3] alias:src_cbo Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select p_mfgr, b.p_name, p_size from part b where b.p_name not in (select p_name from (select p_mfgr, p_name, p_size as r from part) a where r < 10 and b.p_mfgr = a.p_mfgr ) PREHOOK: type: QUERY POSTHOOK: query: explain select p_mfgr, b.p_name, p_size from part b where b.p_name not in (select p_name from (select p_mfgr, p_name, p_size as r from part) a where r < 10 and b.p_mfgr = a.p_mfgr ) POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) Reducer 3 <- Map 6 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 5 <- Map 4 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 3 File Output Operator [FS_25] compressed:false Statistics:Num rows: 15 Data size: 3507 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_24] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 15 Data size: 3507 Basic stats: COMPLETE Column stats: NONE Filter Operator [FIL_28] predicate:_col4 is null (type: boolean) Statistics:Num rows: 15 Data size: 3507 Basic stats: COMPLETE Column stats: NONE Merge Join Operator [MERGEJOIN_33] | condition map:[{"":"Left Outer Join0 to 1"}] | keys:{"1":"_col0 (type: string), _col1 (type: string)","0":"_col0 (type: string), _col1 (type: string)"} | outputColumnNames:["_col0","_col1","_col2","_col4"] | Statistics:Num rows: 30 Data size: 7014 Basic stats: COMPLETE Column stats: NONE |<-Map 6 [SIMPLE_EDGE] | Reduce Output Operator [RS_21] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Statistics:Num rows: 8 Data size: 1752 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_15] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 8 Data size: 1752 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_31] | predicate:(p_size < 10) (type: boolean) | Statistics:Num rows: 8 Data size: 1784 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_13] | alias:b | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_20] key expressions:_col0 (type: string), _col1 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string) sort order:++ Statistics:Num rows: 28 Data size: 6377 Basic stats: COMPLETE Column stats: NONE value expressions:_col2 (type: int) Merge Join Operator [MERGEJOIN_32] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{} | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 28 Data size: 6377 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_17] | sort order: | Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col0 (type: string), _col1 (type: string), _col2 (type: int) | Select Operator [SEL_2] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:b | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 5 [SIMPLE_EDGE] Reduce Output Operator [RS_18] sort order: Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator [SEL_10] Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Filter Operator [FIL_29] predicate:(_col0 = 0) (type: boolean) Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator [GBY_9] | aggregations:["count(VALUE._col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 4 [SIMPLE_EDGE] Reduce Output Operator [RS_8] sort order: Statistics:Num rows: 1 Data size: 231 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: bigint) Group By Operator [GBY_7] aggregations:["count()"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 231 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_5] Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE Filter Operator [FIL_30] predicate:((p_size < 10) and (p_name is null or p_mfgr is null)) (type: boolean) Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE TableScan [TS_3] alias:b Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select p_name, p_size from part where part.p_size not in (select avg(p_size) from (select p_size from part) a where p_size < 10 ) order by p_name PREHOOK: type: QUERY POSTHOOK: query: explain select p_name, p_size from part where part.p_size not in (select avg(p_size) from (select p_size from part) a where p_size < 10 ) order by p_name POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE) Reducer 6 <- Map 5 (SIMPLE_EDGE) Reducer 8 <- Map 7 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 4 File Output Operator [FS_39] compressed:false Statistics:Num rows: 6 Data size: 825 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_38] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 6 Data size: 825 Basic stats: COMPLETE Column stats: NONE |<-Reducer 3 [SIMPLE_EDGE] Reduce Output Operator [RS_37] key expressions:_col0 (type: string) sort order:+ Statistics:Num rows: 6 Data size: 825 Basic stats: COMPLETE Column stats: NONE value expressions:_col1 (type: int) Merge Join Operator [MERGEJOIN_49] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{} | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 6 Data size: 825 Basic stats: COMPLETE Column stats: NONE |<-Reducer 2 [SIMPLE_EDGE] | Reduce Output Operator [RS_31] | sort order: | Statistics:Num rows: 6 Data size: 750 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col0 (type: string), _col1 (type: int) | Filter Operator [FIL_42] | predicate:_col2 is null (type: boolean) | Statistics:Num rows: 6 Data size: 750 Basic stats: COMPLETE Column stats: COMPLETE | Merge Join Operator [MERGEJOIN_48] | | condition map:[{"":"Left Outer Join0 to 1"}] | | keys:{"1":"_col0 (type: double)","0":"UDFToDouble(_col1) (type: double)"} | | outputColumnNames:["_col0","_col1","_col2"] | | Statistics:Num rows: 13 Data size: 1625 Basic stats: COMPLETE Column stats: COMPLETE | |<-Map 1 [SIMPLE_EDGE] | | Reduce Output Operator [RS_28] | | key expressions:UDFToDouble(_col1) (type: double) | | Map-reduce partition columns:UDFToDouble(_col1) (type: double) | | sort order:+ | | Statistics:Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE | | value expressions:_col0 (type: string), _col1 (type: int) | | Select Operator [SEL_2] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE | | TableScan [TS_0] | | alias:part | | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE | |<-Reducer 6 [SIMPLE_EDGE] | Reduce Output Operator [RS_29] | key expressions:_col0 (type: double) | Map-reduce partition columns:_col0 (type: double) | sort order:+ | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE | Group By Operator [GBY_9] | | aggregations:["avg(VALUE._col0)"] | | outputColumnNames:["_col0"] | | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE | |<-Map 5 [SIMPLE_EDGE] | Reduce Output Operator [RS_8] | sort order: | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE | value expressions:_col0 (type: struct) | Group By Operator [GBY_7] | aggregations:["avg(_col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE | Select Operator [SEL_5] | outputColumnNames:["_col0"] | Statistics:Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_44] | predicate:(p_size < 10) (type: boolean) | Statistics:Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_3] | alias:part | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 8 [SIMPLE_EDGE] Reduce Output Operator [RS_32] sort order: Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE Select Operator [SEL_24] Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE Filter Operator [FIL_45] predicate:(_col0 = 0) (type: boolean) Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE Group By Operator [GBY_23] aggregations:["count()"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_18] Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE Filter Operator [FIL_46] predicate:_col0 is null (type: boolean) Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE Group By Operator [GBY_17] | aggregations:["avg(VALUE._col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 7 [SIMPLE_EDGE] Reduce Output Operator [RS_16] sort order: Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE value expressions:_col0 (type: struct) Group By Operator [GBY_15] aggregations:["avg(_col0)"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator [SEL_13] outputColumnNames:["_col0"] Statistics:Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator [FIL_47] predicate:(p_size < 10) (type: boolean) Statistics:Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_11] alias:part Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select b.p_mfgr, min(p_retailprice) from part b group by b.p_mfgr having b.p_mfgr not in (select p_mfgr from (select p_mfgr, min(p_retailprice) l, max(p_retailprice) r, avg(p_retailprice) a from part group by p_mfgr) a where min(p_retailprice) = l and r - l > 600 ) order by b.p_mfgr PREHOOK: type: QUERY POSTHOOK: query: explain select b.p_mfgr, min(p_retailprice) from part b group by b.p_mfgr having b.p_mfgr not in (select p_mfgr from (select p_mfgr, min(p_retailprice) l, max(p_retailprice) r, avg(p_retailprice) a from part group by p_mfgr) a where min(p_retailprice) = l and r - l > 600 ) order by b.p_mfgr POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) Reducer 10 <- Map 9 (SIMPLE_EDGE) Reducer 5 <- Reducer 4 (SIMPLE_EDGE) Reducer 4 <- Reducer 10 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) Reducer 7 <- Map 6 (SIMPLE_EDGE) Reducer 8 <- Reducer 7 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 5 File Output Operator [FS_42] compressed:false Statistics:Num rows: 2 Data size: 256 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_41] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 2 Data size: 256 Basic stats: COMPLETE Column stats: NONE |<-Reducer 4 [SIMPLE_EDGE] Reduce Output Operator [RS_40] key expressions:_col0 (type: string) sort order:+ Statistics:Num rows: 2 Data size: 256 Basic stats: COMPLETE Column stats: NONE value expressions:_col1 (type: double) Select Operator [SEL_39] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 2 Data size: 256 Basic stats: COMPLETE Column stats: NONE Filter Operator [FIL_45] predicate:_col3 is null (type: boolean) Statistics:Num rows: 2 Data size: 256 Basic stats: COMPLETE Column stats: NONE Merge Join Operator [MERGEJOIN_51] | condition map:[{"":"Left Outer Join0 to 1"}] | keys:{"1":"_col0 (type: string), _col1 (type: double)","0":"_col0 (type: string), _col1 (type: double)"} | outputColumnNames:["_col0","_col1","_col3"] | Statistics:Num rows: 5 Data size: 641 Basic stats: COMPLETE Column stats: NONE |<-Reducer 10 [SIMPLE_EDGE] | Reduce Output Operator [RS_36] | key expressions:_col0 (type: string), _col1 (type: double) | Map-reduce partition columns:_col0 (type: string), _col1 (type: double) | sort order:++ | Statistics:Num rows: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_30] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_48] | predicate:((_col2 - _col1) > 600.0) (type: boolean) | Statistics:Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: COMPLETE | Group By Operator [GBY_28] | | aggregations:["min(VALUE._col0)","max(VALUE._col1)"] | | keys:KEY._col0 (type: string) | | outputColumnNames:["_col0","_col1","_col2"] | | Statistics:Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE | |<-Map 9 [SIMPLE_EDGE] | Reduce Output Operator [RS_27] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col1 (type: double), _col2 (type: double) | Group By Operator [GBY_26] | aggregations:["min(_col1)","max(_col1)"] | keys:_col0 (type: string) | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_24] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_23] | alias:b | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 3 [SIMPLE_EDGE] Reduce Output Operator [RS_35] key expressions:_col0 (type: string), _col1 (type: double) Map-reduce partition columns:_col0 (type: string), _col1 (type: double) sort order:++ Statistics:Num rows: 5 Data size: 583 Basic stats: COMPLETE Column stats: NONE Merge Join Operator [MERGEJOIN_50] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{} | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 5 Data size: 583 Basic stats: COMPLETE Column stats: NONE |<-Reducer 2 [SIMPLE_EDGE] | Reduce Output Operator [RS_32] | sort order: | Statistics:Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col0 (type: string), _col1 (type: double) | Group By Operator [GBY_6] | | aggregations:["min(VALUE._col0)"] | | keys:KEY._col0 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE | |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_5] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col1 (type: double) | Group By Operator [GBY_4] | aggregations:["min(_col1)"] | keys:_col0 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_2] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:b | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 8 [SIMPLE_EDGE] Reduce Output Operator [RS_33] sort order: Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator [SEL_20] Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Filter Operator [FIL_46] predicate:(_col0 = 0) (type: boolean) Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator [GBY_19] | aggregations:["count(VALUE._col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 7 [SIMPLE_EDGE] Reduce Output Operator [RS_18] sort order: Statistics:Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: bigint) Group By Operator [GBY_17] aggregations:["count()"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_15] Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE Filter Operator [FIL_47] predicate:((_col0 is null or _col2 is null) and ((_col1 - _col2) > 600.0)) (type: boolean) Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE Group By Operator [GBY_13] | aggregations:["max(VALUE._col0)","min(VALUE._col1)"] | keys:KEY._col0 (type: string) | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 6 [SIMPLE_EDGE] Reduce Output Operator [RS_12] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: double), _col2 (type: double) Group By Operator [GBY_11] aggregations:["max(_col1)","min(_col1)"] keys:_col0 (type: string) outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_9] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_8] alias:b Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select count(c_int) over(), sum(c_float) over(), max(c_int) over(), min(c_int) over(), row_number() over(), rank() over(), dense_rank() over(), percent_rank() over(), lead(c_int, 2, c_int) over(), lag(c_float, 2, c_float) over() from cbo_t1 PREHOOK: type: QUERY POSTHOOK: query: explain select count(c_int) over(), sum(c_float) over(), max(c_int) over(), min(c_int) over(), row_number() over(), rank() over(), dense_rank() over(), percent_rank() over(), lead(c_int, 2, c_int) over(), lag(c_float, 2, c_float) over() from cbo_t1 POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_6] compressed:false Statistics:Num rows: 20 Data size: 1040 Basic stats: COMPLETE Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_4] outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] Statistics:Num rows: 20 Data size: 1040 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator [PTF_3] Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"0","name:":"windowingtablefunction","order by:":"0"}] Statistics:Num rows: 20 Data size: 144 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_2] | outputColumnNames:["_col2","_col3"] | Statistics:Num rows: 20 Data size: 144 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_1] key expressions:0 (type: int) Map-reduce partition columns:0 (type: int) sort order:+ Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE value expressions:c_int (type: int), c_float (type: float) TableScan [TS_0] alias:cbo_t1 Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select * from (select count(c_int) over(), sum(c_float) over(), max(c_int) over(), min(c_int) over(), row_number() over(), rank() over(), dense_rank() over(), percent_rank() over(), lead(c_int, 2, c_int) over(), lag(c_float, 2, c_float) over() from cbo_t1) cbo_t1 PREHOOK: type: QUERY POSTHOOK: query: explain select * from (select count(c_int) over(), sum(c_float) over(), max(c_int) over(), min(c_int) over(), row_number() over(), rank() over(), dense_rank() over(), percent_rank() over(), lead(c_int, 2, c_int) over(), lag(c_float, 2, c_float) over() from cbo_t1) cbo_t1 POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_6] compressed:false Statistics:Num rows: 20 Data size: 1040 Basic stats: COMPLETE Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_4] outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] Statistics:Num rows: 20 Data size: 1040 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator [PTF_3] Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"0","name:":"windowingtablefunction","order by:":"0"}] Statistics:Num rows: 20 Data size: 144 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_2] | outputColumnNames:["_col2","_col3"] | Statistics:Num rows: 20 Data size: 144 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_1] key expressions:0 (type: int) Map-reduce partition columns:0 (type: int) sort order:+ Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE value expressions:c_int (type: int), c_float (type: float) TableScan [TS_0] alias:cbo_t1 Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select i, a, h, b, c, d, e, f, g, a as x, a +1 as y from (select max(c_int) over (partition by key order by value range UNBOUNDED PRECEDING) a, min(c_int) over (partition by key order by value range current row) b, count(c_int) over(partition by key order by value range 1 PRECEDING) c, avg(value) over (partition by key order by value range between unbounded preceding and unbounded following) d, sum(value) over (partition by key order by value range between unbounded preceding and current row) e, avg(c_float) over (partition by key order by value range between 1 preceding and unbounded following) f, sum(c_float) over (partition by key order by value range between 1 preceding and current row) g, max(c_float) over (partition by key order by value range between 1 preceding and unbounded following) h, min(c_float) over (partition by key order by value range between 1 preceding and 1 following) i from cbo_t1) cbo_t1 PREHOOK: type: QUERY POSTHOOK: query: explain select i, a, h, b, c, d, e, f, g, a as x, a +1 as y from (select max(c_int) over (partition by key order by value range UNBOUNDED PRECEDING) a, min(c_int) over (partition by key order by value range current row) b, count(c_int) over(partition by key order by value range 1 PRECEDING) c, avg(value) over (partition by key order by value range between unbounded preceding and unbounded following) d, sum(value) over (partition by key order by value range between unbounded preceding and current row) e, avg(c_float) over (partition by key order by value range between 1 preceding and unbounded following) f, sum(c_float) over (partition by key order by value range between 1 preceding and current row) g, max(c_float) over (partition by key order by value range between 1 preceding and unbounded following) h, min(c_float) over (partition by key order by value range between 1 preceding and 1 following) i from cbo_t1) cbo_t1 POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_6] compressed:false Statistics:Num rows: 20 Data size: 1280 Basic stats: COMPLETE Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_4] outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"] Statistics:Num rows: 20 Data size: 1280 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator [PTF_3] Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"_col0","name:":"windowingtablefunction","order by:":"_col1"}] Statistics:Num rows: 20 Data size: 3204 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_2] | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 20 Data size: 3204 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_1] key expressions:key (type: string), value (type: string) Map-reduce partition columns:key (type: string) sort order:++ Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE value expressions:c_int (type: int), c_float (type: float) TableScan [TS_0] alias:cbo_t1 Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select *, rank() over(partition by key order by value) as rr from src1 PREHOOK: type: QUERY POSTHOOK: query: explain select *, rank() over(partition by key order by value) as rr from src1 POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_6] compressed:false Statistics:Num rows: 25 Data size: 4475 Basic stats: COMPLETE Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_4] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 25 Data size: 4475 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator [PTF_3] Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"_col0","name:":"windowingtablefunction","order by:":"_col1"}] Statistics:Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_2] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_1] key expressions:key (type: string), value (type: string) Map-reduce partition columns:key (type: string) sort order:++ Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_0] alias:src1 Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) FROM (select x.key AS key, count(1) AS cnt FROM src1 x JOIN src y ON (x.key = y.key) GROUP BY x.key) tmp PREHOOK: type: QUERY POSTHOOK: query: explain select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) FROM (select x.key AS key, count(1) AS cnt FROM src1 x JOIN src y ON (x.key = y.key) GROUP BY x.key) tmp POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 4 File Output Operator [FS_20] compressed:false Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Group By Operator [GBY_18] | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 3 [SIMPLE_EDGE] Reduce Output Operator [RS_17] sort order: Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: bigint), _col1 (type: bigint) Group By Operator [GBY_16] aggregations:["sum(_col0)","sum(_col1)"] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_14] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator [GBY_13] | aggregations:["count(VALUE._col0)"] | keys:KEY._col0 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_12] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: bigint) Group By Operator [GBY_11] aggregations:["count(1)"] keys:_col0 (type: string) outputColumnNames:["_col0","_col1"] Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_9] outputColumnNames:["_col0"] Statistics:Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator [MERGEJOIN_25] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} | outputColumnNames:["_col1"] | Statistics:Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_5] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_1] | outputColumnNames:["_col0"] | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_23] | predicate:key is not null (type: boolean) | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:y | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 5 [SIMPLE_EDGE] Reduce Output Operator [RS_7] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_3] outputColumnNames:["_col0"] Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator [FIL_24] predicate:key is not null (type: boolean) Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_2] alias:x Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) FROM (select x.key AS key, count(1) AS cnt FROM src1 x JOIN src y ON (x.key = y.key) GROUP BY x.key) tmp PREHOOK: type: QUERY POSTHOOK: query: explain select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) FROM (select x.key AS key, count(1) AS cnt FROM src1 x JOIN src y ON (x.key = y.key) GROUP BY x.key) tmp POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 4 File Output Operator [FS_20] compressed:false Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Group By Operator [GBY_18] | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 3 [SIMPLE_EDGE] Reduce Output Operator [RS_17] sort order: Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: bigint), _col1 (type: bigint) Group By Operator [GBY_16] aggregations:["sum(_col0)","sum(_col1)"] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_14] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator [GBY_13] | aggregations:["count(VALUE._col0)"] | keys:KEY._col0 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_12] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: bigint) Group By Operator [GBY_11] aggregations:["count(1)"] keys:_col0 (type: string) outputColumnNames:["_col0","_col1"] Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_9] outputColumnNames:["_col0"] Statistics:Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator [MERGEJOIN_25] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} | outputColumnNames:["_col1"] | Statistics:Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_5] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_1] | outputColumnNames:["_col0"] | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_23] | predicate:key is not null (type: boolean) | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:y | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 5 [SIMPLE_EDGE] Reduce Output Operator [RS_7] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_3] outputColumnNames:["_col0"] Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator [FIL_24] predicate:key is not null (type: boolean) Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_2] alias:x Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) FROM (select x.key AS key, count(1) AS cnt FROM src1 x JOIN src y ON (x.key = y.key) GROUP BY x.key) tmp PREHOOK: type: QUERY POSTHOOK: query: explain select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) FROM (select x.key AS key, count(1) AS cnt FROM src1 x JOIN src y ON (x.key = y.key) GROUP BY x.key) tmp POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Map 1 <- Map 4 (BROADCAST_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 3 File Output Operator [FS_20] compressed:false Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Group By Operator [GBY_18] | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_17] sort order: Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: bigint), _col1 (type: bigint) Group By Operator [GBY_16] aggregations:["sum(_col0)","sum(_col1)"] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_14] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator [GBY_13] | aggregations:["count(VALUE._col0)"] | keys:KEY._col0 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_12] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: bigint) Group By Operator [GBY_11] aggregations:["count(1)"] keys:_col0 (type: string) outputColumnNames:["_col0","_col1"] Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_9] outputColumnNames:["_col0"] Statistics:Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator [MAPJOIN_25] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"Map 1":"_col0 (type: string)","Map 4":"_col0 (type: string)"} | outputColumnNames:["_col1"] | Statistics:Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 4 [BROADCAST_EDGE] | Reduce Output Operator [RS_7] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_3] | outputColumnNames:["_col0"] | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_24] | predicate:key is not null (type: boolean) | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_2] | alias:x | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE |<-Select Operator [SEL_1] outputColumnNames:["_col0"] Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator [FIL_23] predicate:key is not null (type: boolean) Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_0] alias:y Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) FROM (select x.key AS key, count(1) AS cnt FROM src1 x LEFT SEMI JOIN src y ON (x.key = y.key) GROUP BY x.key) tmp PREHOOK: type: QUERY POSTHOOK: query: explain select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) FROM (select x.key AS key, count(1) AS cnt FROM src1 x LEFT SEMI JOIN src y ON (x.key = y.key) GROUP BY x.key) tmp POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 4 File Output Operator [FS_22] compressed:false Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Group By Operator [GBY_20] | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 3 [SIMPLE_EDGE] Reduce Output Operator [RS_19] sort order: Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: bigint), _col1 (type: bigint) Group By Operator [GBY_18] aggregations:["sum(_col0)","sum(_col1)"] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_16] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator [GBY_15] | aggregations:["count(VALUE._col0)"] | keys:KEY._col0 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_14] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: bigint) Group By Operator [GBY_13] aggregations:["count(1)"] keys:_col0 (type: string) outputColumnNames:["_col0","_col1"] Statistics:Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator [MERGEJOIN_27] | condition map:[{"":"Left Semi Join 0 to 1"}] | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} | outputColumnNames:["_col0"] | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_7] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_1] | outputColumnNames:["_col0"] | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_25] | predicate:key is not null (type: boolean) | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:x | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 5 [SIMPLE_EDGE] Reduce Output Operator [RS_9] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 205 Data size: 17835 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator [GBY_5] keys:_col0 (type: string) outputColumnNames:["_col0"] Statistics:Num rows: 205 Data size: 17835 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_3] outputColumnNames:["_col0"] Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator [FIL_26] predicate:key is not null (type: boolean) Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_2] alias:y Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain create table abcd (a int, b int, c int, d int) PREHOOK: type: CREATETABLE POSTHOOK: query: explain create table abcd (a int, b int, c int, d int) POSTHOOK: type: CREATETABLE Stage-0 Create Table Operator: columns:["a int","b int","c int","d int"] input format:org.apache.hadoop.mapred.TextInputFormat name:default.abcd output format:org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat PREHOOK: query: create table abcd (a int, b int, c int, d int) PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@abcd POSTHOOK: query: create table abcd (a int, b int, c int, d int) POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@abcd PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/in4.txt' INTO TABLE abcd PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@abcd POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/in4.txt' INTO TABLE abcd POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@abcd PREHOOK: query: explain select a, count(distinct b), count(distinct c), sum(d) from abcd group by a PREHOOK: type: QUERY POSTHOOK: query: explain select a, count(distinct b), count(distinct c), sum(d) from abcd group by a POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_7] compressed:false Statistics:Num rows: 2 Data size: 39 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Group By Operator [GBY_5] | aggregations:["count(DISTINCT KEY._col1:0._col0)","count(DISTINCT KEY._col1:1._col0)","sum(VALUE._col2)"] | keys:KEY._col0 (type: int) | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 2 Data size: 39 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_4] key expressions:_col0 (type: int), _col1 (type: int), _col2 (type: int) Map-reduce partition columns:_col0 (type: int) sort order:+++ Statistics:Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE value expressions:_col5 (type: bigint) Group By Operator [GBY_3] aggregations:["count(DISTINCT _col1)","count(DISTINCT _col2)","sum(_col3)"] keys:_col0 (type: int), _col1 (type: int), _col2 (type: int) outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] Statistics:Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Select Operator [SEL_1] outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE TableScan [TS_0] alias:abcd Statistics:Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: explain select a, count(distinct b), count(distinct c), sum(d) from abcd group by a PREHOOK: type: QUERY POSTHOOK: query: explain select a, count(distinct b), count(distinct c), sum(d) from abcd group by a POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_6] compressed:false Statistics:Num rows: 2 Data size: 39 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Group By Operator [GBY_4] | aggregations:["count(DISTINCT KEY._col1:0._col0)","count(DISTINCT KEY._col1:1._col0)","sum(VALUE._col0)"] | keys:KEY._col0 (type: int) | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 2 Data size: 39 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_3] key expressions:_col0 (type: int), _col1 (type: int), _col2 (type: int) Map-reduce partition columns:_col0 (type: int) sort order:+++ Statistics:Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE value expressions:_col3 (type: int) Select Operator [SEL_1] outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE TableScan [TS_0] alias:abcd Statistics:Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: explain create table src_rc_merge_test(key int, value string) stored as rcfile PREHOOK: type: CREATETABLE POSTHOOK: query: explain create table src_rc_merge_test(key int, value string) stored as rcfile POSTHOOK: type: CREATETABLE Stage-0 Create Table Operator: columns:["key int","value string"] input format:org.apache.hadoop.hive.ql.io.RCFileInputFormat name:default.src_rc_merge_test output format:org.apache.hadoop.hive.ql.io.RCFileOutputFormat PREHOOK: query: create table src_rc_merge_test(key int, value string) stored as rcfile PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@src_rc_merge_test POSTHOOK: query: create table src_rc_merge_test(key int, value string) stored as rcfile POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@src_rc_merge_test PREHOOK: query: load data local inpath '../../data/files/smbbucket_1.rc' into table src_rc_merge_test PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@src_rc_merge_test POSTHOOK: query: load data local inpath '../../data/files/smbbucket_1.rc' into table src_rc_merge_test POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@src_rc_merge_test PREHOOK: query: explain create table tgt_rc_merge_test(key int, value string) stored as rcfile PREHOOK: type: CREATETABLE POSTHOOK: query: explain create table tgt_rc_merge_test(key int, value string) stored as rcfile POSTHOOK: type: CREATETABLE Stage-0 Create Table Operator: columns:["key int","value string"] input format:org.apache.hadoop.hive.ql.io.RCFileInputFormat name:default.tgt_rc_merge_test output format:org.apache.hadoop.hive.ql.io.RCFileOutputFormat PREHOOK: query: create table tgt_rc_merge_test(key int, value string) stored as rcfile PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@tgt_rc_merge_test POSTHOOK: query: create table tgt_rc_merge_test(key int, value string) stored as rcfile POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@tgt_rc_merge_test PREHOOK: query: insert into table tgt_rc_merge_test select * from src_rc_merge_test PREHOOK: type: QUERY PREHOOK: Input: default@src_rc_merge_test PREHOOK: Output: default@tgt_rc_merge_test POSTHOOK: query: insert into table tgt_rc_merge_test select * from src_rc_merge_test POSTHOOK: type: QUERY POSTHOOK: Input: default@src_rc_merge_test POSTHOOK: Output: default@tgt_rc_merge_test POSTHOOK: Lineage: tgt_rc_merge_test.key SIMPLE [(src_rc_merge_test)src_rc_merge_test.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: tgt_rc_merge_test.value SIMPLE [(src_rc_merge_test)src_rc_merge_test.FieldSchema(name:value, type:string, comment:null), ] PREHOOK: query: show table extended like `tgt_rc_merge_test` PREHOOK: type: SHOW_TABLESTATUS POSTHOOK: query: show table extended like `tgt_rc_merge_test` POSTHOOK: type: SHOW_TABLESTATUS tableName:tgt_rc_merge_test #### A masked pattern was here #### inputformat:org.apache.hadoop.hive.ql.io.RCFileInputFormat outputformat:org.apache.hadoop.hive.ql.io.RCFileOutputFormat columns:struct columns { i32 key, string value} partitioned:false partitionColumns: totalNumberFiles:1 totalFileSize:171 maxFileSize:171 minFileSize:171 #### A masked pattern was here #### PREHOOK: query: explain select count(1) from tgt_rc_merge_test PREHOOK: type: QUERY POSTHOOK: query: explain select count(1) from tgt_rc_merge_test POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_6] compressed:true Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Group By Operator [GBY_4] | aggregations:["count(1)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_3] sort order: Statistics:Num rows: 5 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_1] Statistics:Num rows: 5 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_0] alias:tgt_rc_merge_test Statistics:Num rows: 5 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select sum(hash(key)), sum(hash(value)) from tgt_rc_merge_test PREHOOK: type: QUERY POSTHOOK: query: explain select sum(hash(key)), sum(hash(value)) from tgt_rc_merge_test POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_6] compressed:true Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Group By Operator [GBY_4] | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_3] sort order: Statistics:Num rows: 5 Data size: 32 Basic stats: COMPLETE Column stats: NONE value expressions:_col0 (type: int), _col1 (type: int) Select Operator [SEL_1] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 5 Data size: 32 Basic stats: COMPLETE Column stats: NONE TableScan [TS_0] alias:tgt_rc_merge_test Statistics:Num rows: 5 Data size: 32 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: alter table tgt_rc_merge_test concatenate PREHOOK: type: ALTER_TABLE_MERGE PREHOOK: Input: default@tgt_rc_merge_test PREHOOK: Output: default@tgt_rc_merge_test POSTHOOK: query: alter table tgt_rc_merge_test concatenate POSTHOOK: type: ALTER_TABLE_MERGE POSTHOOK: Input: default@tgt_rc_merge_test POSTHOOK: Output: default@tgt_rc_merge_test PREHOOK: query: show table extended like `tgt_rc_merge_test` PREHOOK: type: SHOW_TABLESTATUS POSTHOOK: query: show table extended like `tgt_rc_merge_test` POSTHOOK: type: SHOW_TABLESTATUS tableName:tgt_rc_merge_test #### A masked pattern was here #### inputformat:org.apache.hadoop.hive.ql.io.RCFileInputFormat outputformat:org.apache.hadoop.hive.ql.io.RCFileOutputFormat columns:struct columns { i32 key, string value} partitioned:false partitionColumns: totalNumberFiles:1 totalFileSize:171 maxFileSize:171 minFileSize:171 #### A masked pattern was here #### PREHOOK: query: explain select count(1) from tgt_rc_merge_test PREHOOK: type: QUERY POSTHOOK: query: explain select count(1) from tgt_rc_merge_test POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_6] compressed:true Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Group By Operator [GBY_4] | aggregations:["count(1)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_3] sort order: Statistics:Num rows: 0 Data size: 171 Basic stats: PARTIAL Column stats: COMPLETE Select Operator [SEL_1] Statistics:Num rows: 0 Data size: 171 Basic stats: PARTIAL Column stats: COMPLETE TableScan [TS_0] alias:tgt_rc_merge_test Statistics:Num rows: 0 Data size: 171 Basic stats: PARTIAL Column stats: COMPLETE PREHOOK: query: explain select sum(hash(key)), sum(hash(value)) from tgt_rc_merge_test PREHOOK: type: QUERY POSTHOOK: query: explain select sum(hash(key)), sum(hash(value)) from tgt_rc_merge_test POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_6] compressed:true Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Group By Operator [GBY_4] | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_3] sort order: Statistics:Num rows: 1 Data size: 171 Basic stats: COMPLETE Column stats: NONE value expressions:_col0 (type: int), _col1 (type: int) Select Operator [SEL_1] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 1 Data size: 171 Basic stats: COMPLETE Column stats: NONE TableScan [TS_0] alias:tgt_rc_merge_test Statistics:Num rows: 1 Data size: 171 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: drop table src_rc_merge_test PREHOOK: type: DROPTABLE PREHOOK: Input: default@src_rc_merge_test PREHOOK: Output: default@src_rc_merge_test POSTHOOK: query: drop table src_rc_merge_test POSTHOOK: type: DROPTABLE POSTHOOK: Input: default@src_rc_merge_test POSTHOOK: Output: default@src_rc_merge_test PREHOOK: query: drop table tgt_rc_merge_test PREHOOK: type: DROPTABLE PREHOOK: Input: default@tgt_rc_merge_test PREHOOK: Output: default@tgt_rc_merge_test POSTHOOK: query: drop table tgt_rc_merge_test POSTHOOK: type: DROPTABLE POSTHOOK: Input: default@tgt_rc_merge_test POSTHOOK: Output: default@tgt_rc_merge_test PREHOOK: query: explain select src.key from src cross join src src2 PREHOOK: type: QUERY POSTHOOK: query: explain select src.key from src cross join src src2 POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_9] compressed:true Statistics:Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Merge Join Operator [MERGEJOIN_11] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{} | outputColumnNames:["_col0"] | Statistics:Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_5] | sort order: | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col0 (type: string) | Select Operator [SEL_1] | outputColumnNames:["_col0"] | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:src | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 3 [SIMPLE_EDGE] Reduce Output Operator [RS_6] sort order: Statistics:Num rows: 500 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator [SEL_3] Statistics:Num rows: 500 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE TableScan [TS_2] alias:src Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain create table nzhang_Tmp(a int, b string) PREHOOK: type: CREATETABLE POSTHOOK: query: explain create table nzhang_Tmp(a int, b string) POSTHOOK: type: CREATETABLE Stage-0 Create Table Operator: columns:["a int","b string"] input format:org.apache.hadoop.mapred.TextInputFormat name:default.nzhang_Tmp output format:org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat PREHOOK: query: create table nzhang_Tmp(a int, b string) PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@nzhang_Tmp POSTHOOK: query: create table nzhang_Tmp(a int, b string) POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@nzhang_Tmp PREHOOK: query: explain create table nzhang_CTAS1 as select key k, value from src sort by k, value limit 10 PREHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: query: explain create table nzhang_CTAS1 as select key k, value from src sort by k, value limit 10 POSTHOOK: type: CREATETABLE_AS_SELECT Plan not optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Stage-3 Stats-Aggr Operator Stage-4 Create Table Operator: columns:["k string","value string"] input format:org.apache.hadoop.mapred.TextInputFormat name:default.nzhang_CTAS1 output format:org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat Stage-2 Dependency Collection{} Stage-1 Reducer 3 File Output Operator [FS_8] compressed:true Statistics:Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.nzhang_CTAS1","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Limit [LIM_7] Number of rows:10 Statistics:Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_6] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_5] key expressions:_col0 (type: string), _col1 (type: string) sort order:++ Statistics:Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Limit [LIM_4] Number of rows:10 Statistics:Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_3] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_2] key expressions:_col0 (type: string), _col1 (type: string) sort order:++ Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_1] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_0] alias:src Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Stage-0 Move Operator Please refer to the previous Stage-1 PREHOOK: query: create table nzhang_CTAS1 as select key k, value from src sort by k, value limit 10 PREHOOK: type: CREATETABLE_AS_SELECT PREHOOK: Input: default@src PREHOOK: Output: database:default PREHOOK: Output: default@nzhang_CTAS1 POSTHOOK: query: create table nzhang_CTAS1 as select key k, value from src sort by k, value limit 10 POSTHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: Input: default@src POSTHOOK: Output: database:default POSTHOOK: Output: default@nzhang_CTAS1 PREHOOK: query: explain create table nzhang_ctas3 row format serde "org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe" stored as RCFile as select key/2 half_key, concat(value, "_con") conb from src sort by half_key, conb limit 10 PREHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: query: explain create table nzhang_ctas3 row format serde "org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe" stored as RCFile as select key/2 half_key, concat(value, "_con") conb from src sort by half_key, conb limit 10 POSTHOOK: type: CREATETABLE_AS_SELECT Plan not optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Stage-3 Stats-Aggr Operator Stage-4 Create Table Operator: columns:["half_key double","conb string"] input format:org.apache.hadoop.hive.ql.io.RCFileInputFormat name:default.nzhang_ctas3 output format:org.apache.hadoop.hive.ql.io.RCFileOutputFormat Stage-2 Dependency Collection{} Stage-1 Reducer 3 File Output Operator [FS_8] compressed:true Statistics:Num rows: 10 Data size: 1920 Basic stats: COMPLETE Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe","name:":"default.nzhang_ctas3","input format:":"org.apache.hadoop.hive.ql.io.RCFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.RCFileOutputFormat"} Limit [LIM_7] Number of rows:10 Statistics:Num rows: 10 Data size: 1920 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_6] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 10 Data size: 1920 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_5] key expressions:_col0 (type: double), _col1 (type: string) sort order:++ Statistics:Num rows: 10 Data size: 1920 Basic stats: COMPLETE Column stats: COMPLETE Limit [LIM_4] Number of rows:10 Statistics:Num rows: 10 Data size: 1920 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_3] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 500 Data size: 96000 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_2] key expressions:_col0 (type: double), _col1 (type: string) sort order:++ Statistics:Num rows: 500 Data size: 96000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_1] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 500 Data size: 96000 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_0] alias:src Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Stage-0 Move Operator Please refer to the previous Stage-1 PREHOOK: query: create table nzhang_ctas3 row format serde "org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe" stored as RCFile as select key/2 half_key, concat(value, "_con") conb from src sort by half_key, conb limit 10 PREHOOK: type: CREATETABLE_AS_SELECT PREHOOK: Input: default@src PREHOOK: Output: database:default PREHOOK: Output: default@nzhang_ctas3 POSTHOOK: query: create table nzhang_ctas3 row format serde "org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe" stored as RCFile as select key/2 half_key, concat(value, "_con") conb from src sort by half_key, conb limit 10 POSTHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: Input: default@src POSTHOOK: Output: database:default POSTHOOK: Output: default@nzhang_ctas3 PREHOOK: query: explain create table if not exists nzhang_ctas3 as select key, value from src sort by key, value limit 2 PREHOOK: type: CREATETABLE POSTHOOK: query: explain create table if not exists nzhang_ctas3 as select key, value from src sort by key, value limit 2 POSTHOOK: type: CREATETABLE PREHOOK: query: create table if not exists nzhang_ctas3 as select key, value from src sort by key, value limit 2 PREHOOK: type: CREATETABLE POSTHOOK: query: create table if not exists nzhang_ctas3 as select key, value from src sort by key, value limit 2 POSTHOOK: type: CREATETABLE PREHOOK: query: explain create temporary table acid_dtt(a int, b varchar(128)) clustered by (a) into 2 buckets stored as orc TBLPROPERTIES ('transactional'='true') PREHOOK: type: CREATETABLE POSTHOOK: query: explain create temporary table acid_dtt(a int, b varchar(128)) clustered by (a) into 2 buckets stored as orc TBLPROPERTIES ('transactional'='true') POSTHOOK: type: CREATETABLE Stage-0 Create Table Operator: # buckets:2 bucket columns:["a"] columns:["a int","b varchar(128)"] input format:org.apache.hadoop.hive.ql.io.orc.OrcInputFormat name:default.acid_dtt output format:org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat PREHOOK: query: create temporary table acid_dtt(a int, b varchar(128)) clustered by (a) into 2 buckets stored as orc TBLPROPERTIES ('transactional'='true') PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@acid_dtt POSTHOOK: query: create temporary table acid_dtt(a int, b varchar(128)) clustered by (a) into 2 buckets stored as orc TBLPROPERTIES ('transactional'='true') POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@acid_dtt PREHOOK: query: explain select src1.key as k1, src1.value as v1, src2.key as k2, src2.value as v2 FROM (select * FROM src WHERE src.key < 10) src1 JOIN (select * FROM src WHERE src.key < 10) src2 SORT BY k1, v1, k2, v2 PREHOOK: type: QUERY POSTHOOK: query: explain select src1.key as k1, src1.value as v1, src2.key as k2, src2.value as v2 FROM (select * FROM src WHERE src.key < 10) src1 JOIN (select * FROM src WHERE src.key < 10) src2 SORT BY k1, v1, k2, v2 POSTHOOK: type: QUERY Plan not optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 3 File Output Operator [FS_12] compressed:true Statistics:Num rows: 13778 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_11] | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 13778 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_10] key expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) sort order:++++ Statistics:Num rows: 13778 Data size: 4904968 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator [MERGEJOIN_15] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{} | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 13778 Data size: 4904968 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_6] | sort order: | Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col0 (type: string), _col1 (type: string) | Select Operator [SEL_2] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_13] | predicate:(key < 10) (type: boolean) | Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:src | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 4 [SIMPLE_EDGE] Reduce Output Operator [RS_7] sort order: Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: string), _col1 (type: string) Select Operator [SEL_5] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator [FIL_14] predicate:(key < 10) (type: boolean) Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_3] alias:src Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE 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/in8.txt' INTO TABLE myinput1 PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@myinput1 POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/in8.txt' INTO TABLE myinput1 POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@myinput1 PREHOOK: query: explain select * from myinput1 a join myinput1 b on a.key<=>b.value PREHOOK: type: QUERY POSTHOOK: query: explain select * from myinput1 a join myinput1 b on a.key<=>b.value POSTHOOK: type: QUERY Plan not optimized by CBO due to missing feature [Less_than_equal_greater_than]. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_6] compressed:true Statistics:Num rows: 3 Data size: 28 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_5] outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 3 Data size: 28 Basic stats: COMPLETE Column stats: NONE Merge Join Operator [MERGEJOIN_7] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"1":"value (type: int)","0":"key (type: int)"} | outputColumnNames:["_col0","_col1","_col5","_col6"] | Statistics:Num rows: 3 Data size: 28 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_2] | key expressions:key (type: int) | Map-reduce partition columns:key (type: int) | sort order:+ | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE | value expressions:value (type: int) | TableScan [TS_0] | alias:a | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE |<-Map 3 [SIMPLE_EDGE] Reduce Output Operator [RS_3] key expressions:value (type: int) Map-reduce partition columns:value (type: int) sort order:+ Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE value expressions:key (type: int) TableScan [TS_1] alias:b Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: explain select * from myinput1 a join myinput1 b on a.key<=>b.value join myinput1 c on a.key=c.key PREHOOK: type: QUERY POSTHOOK: query: explain select * from myinput1 a join myinput1 b on a.key<=>b.value join myinput1 c on a.key=c.key POSTHOOK: type: QUERY Plan not optimized by CBO due to missing feature [Less_than_equal_greater_than]. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_11] compressed:true Statistics:Num rows: 4 Data size: 37 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_10] outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] Statistics:Num rows: 4 Data size: 37 Basic stats: COMPLETE Column stats: NONE Merge Join Operator [MERGEJOIN_21] | condition map:[{"":"Inner Join 0 to 1"},{"":"Inner Join 0 to 2"}] | keys:{"2":"key (type: int)","1":"value (type: int)","0":"key (type: int)"} | outputColumnNames:["_col0","_col1","_col5","_col6","_col10","_col11"] | Statistics:Num rows: 4 Data size: 37 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_4] | key expressions:key (type: int) | Map-reduce partition columns:key (type: int) | sort order:+ | Statistics:Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE | value expressions:value (type: int) | Filter Operator [FIL_18] | predicate:key is not null (type: boolean) | Statistics:Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_0] | alias:a | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE |<-Map 3 [SIMPLE_EDGE] | Reduce Output Operator [RS_6] | key expressions:value (type: int) | Map-reduce partition columns:value (type: int) | sort order:+ | Statistics:Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE | value expressions:key (type: int) | Filter Operator [FIL_19] | predicate:value is not null (type: boolean) | Statistics:Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_1] | alias:b | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE |<-Map 4 [SIMPLE_EDGE] Reduce Output Operator [RS_8] key expressions:key (type: int) Map-reduce partition columns:key (type: int) sort order:+ Statistics:Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE value expressions:value (type: int) Filter Operator [FIL_20] predicate:key is not null (type: boolean) Statistics:Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE TableScan [TS_2] alias:c Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: explain select * from myinput1 a join myinput1 b on a.key<=>b.value join myinput1 c on a.key<=>c.key PREHOOK: type: QUERY POSTHOOK: query: explain select * from myinput1 a join myinput1 b on a.key<=>b.value join myinput1 c on a.key<=>c.key POSTHOOK: type: QUERY Plan not optimized by CBO due to missing feature [Less_than_equal_greater_than]. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_8] compressed:true Statistics:Num rows: 6 Data size: 57 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_7] outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] Statistics:Num rows: 6 Data size: 57 Basic stats: COMPLETE Column stats: NONE Merge Join Operator [MERGEJOIN_9] | condition map:[{"":"Inner Join 0 to 1"},{"":"Inner Join 0 to 2"}] | keys:{"2":"key (type: int)","1":"value (type: int)","0":"key (type: int)"} | outputColumnNames:["_col0","_col1","_col5","_col6","_col10","_col11"] | Statistics:Num rows: 6 Data size: 57 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_3] | key expressions:key (type: int) | Map-reduce partition columns:key (type: int) | sort order:+ | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE | value expressions:value (type: int) | TableScan [TS_0] | alias:a | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE |<-Map 3 [SIMPLE_EDGE] | Reduce Output Operator [RS_4] | key expressions:value (type: int) | Map-reduce partition columns:value (type: int) | sort order:+ | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE | value expressions:key (type: int) | TableScan [TS_1] | alias:b | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE |<-Map 4 [SIMPLE_EDGE] Reduce Output Operator [RS_5] key expressions:key (type: int) Map-reduce partition columns:key (type: int) sort order:+ Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE value expressions:value (type: int) TableScan [TS_2] alias:c Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: explain select * from myinput1 a join myinput1 b on a.key<=>b.value AND a.value=b.key join myinput1 c on a.key<=>c.key AND a.value=c.value PREHOOK: type: QUERY POSTHOOK: query: explain select * from myinput1 a join myinput1 b on a.key<=>b.value AND a.value=b.key join myinput1 c on a.key<=>c.key AND a.value=c.value POSTHOOK: type: QUERY Plan not optimized by CBO due to missing feature [Less_than_equal_greater_than]. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_11] compressed:true Statistics:Num rows: 4 Data size: 37 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_10] outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] Statistics:Num rows: 4 Data size: 37 Basic stats: COMPLETE Column stats: NONE Merge Join Operator [MERGEJOIN_15] | condition map:[{"":"Inner Join 0 to 1"},{"":"Inner Join 0 to 2"}] | keys:{"2":"key (type: int), value (type: int)","1":"value (type: int), key (type: int)","0":"key (type: int), value (type: int)"} | outputColumnNames:["_col0","_col1","_col5","_col6","_col10","_col11"] | Statistics:Num rows: 4 Data size: 37 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_4] | key expressions:key (type: int), value (type: int) | Map-reduce partition columns:key (type: int), value (type: int) | sort order:++ | Statistics:Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE | Filter Operator [FIL_12] | predicate:value is not null (type: boolean) | Statistics:Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_0] | alias:a | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE |<-Map 3 [SIMPLE_EDGE] | Reduce Output Operator [RS_6] | key expressions:value (type: int), key (type: int) | Map-reduce partition columns:value (type: int), key (type: int) | sort order:++ | Statistics:Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE | Filter Operator [FIL_13] | predicate:key is not null (type: boolean) | Statistics:Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_1] | alias:b | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE |<-Map 4 [SIMPLE_EDGE] Reduce Output Operator [RS_8] key expressions:key (type: int), value (type: int) Map-reduce partition columns:key (type: int), value (type: int) sort order:++ Statistics:Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE Filter Operator [FIL_14] predicate:value is not null (type: boolean) Statistics:Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE TableScan [TS_2] alias:c Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: explain select * from myinput1 a join myinput1 b on a.key<=>b.value AND a.value<=>b.key join myinput1 c on a.key<=>c.key AND a.value<=>c.value PREHOOK: type: QUERY POSTHOOK: query: explain select * from myinput1 a join myinput1 b on a.key<=>b.value AND a.value<=>b.key join myinput1 c on a.key<=>c.key AND a.value<=>c.value POSTHOOK: type: QUERY Plan not optimized by CBO due to missing feature [Less_than_equal_greater_than]. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_8] compressed:true Statistics:Num rows: 6 Data size: 57 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_7] outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] Statistics:Num rows: 6 Data size: 57 Basic stats: COMPLETE Column stats: NONE Merge Join Operator [MERGEJOIN_9] | condition map:[{"":"Inner Join 0 to 1"},{"":"Inner Join 0 to 2"}] | keys:{"2":"key (type: int), value (type: int)","1":"value (type: int), key (type: int)","0":"key (type: int), value (type: int)"} | outputColumnNames:["_col0","_col1","_col5","_col6","_col10","_col11"] | Statistics:Num rows: 6 Data size: 57 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_3] | key expressions:key (type: int), value (type: int) | Map-reduce partition columns:key (type: int), value (type: int) | sort order:++ | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_0] | alias:a | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE |<-Map 3 [SIMPLE_EDGE] | Reduce Output Operator [RS_4] | key expressions:value (type: int), key (type: int) | Map-reduce partition columns:value (type: int), key (type: int) | sort order:++ | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_1] | alias:b | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE |<-Map 4 [SIMPLE_EDGE] Reduce Output Operator [RS_5] key expressions:key (type: int), value (type: int) Map-reduce partition columns:key (type: int), value (type: int) sort order:++ Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE TableScan [TS_2] alias:c Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: explain select * FROM myinput1 a LEFT OUTER JOIN myinput1 b ON a.key<=>b.value PREHOOK: type: QUERY POSTHOOK: query: explain select * FROM myinput1 a LEFT OUTER JOIN myinput1 b ON a.key<=>b.value POSTHOOK: type: QUERY Plan not optimized by CBO due to missing feature [Less_than_equal_greater_than]. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_6] compressed:true Statistics:Num rows: 3 Data size: 28 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_5] outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 3 Data size: 28 Basic stats: COMPLETE Column stats: NONE Merge Join Operator [MERGEJOIN_7] | condition map:[{"":"Left Outer Join0 to 1"}] | keys:{"1":"value (type: int)","0":"key (type: int)"} | outputColumnNames:["_col0","_col1","_col5","_col6"] | Statistics:Num rows: 3 Data size: 28 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_2] | key expressions:key (type: int) | Map-reduce partition columns:key (type: int) | sort order:+ | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE | value expressions:value (type: int) | TableScan [TS_0] | alias:a | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE |<-Map 3 [SIMPLE_EDGE] Reduce Output Operator [RS_3] key expressions:value (type: int) Map-reduce partition columns:value (type: int) sort order:+ Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE value expressions:key (type: int) TableScan [TS_1] alias:b Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: explain select * FROM myinput1 a RIGHT OUTER JOIN myinput1 b ON a.key<=>b.value PREHOOK: type: QUERY POSTHOOK: query: explain select * FROM myinput1 a RIGHT OUTER JOIN myinput1 b ON a.key<=>b.value POSTHOOK: type: QUERY Plan not optimized by CBO due to missing feature [Less_than_equal_greater_than]. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_6] compressed:true Statistics:Num rows: 3 Data size: 28 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_5] outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 3 Data size: 28 Basic stats: COMPLETE Column stats: NONE Merge Join Operator [MERGEJOIN_7] | condition map:[{"":"Right Outer Join0 to 1"}] | keys:{"1":"value (type: int)","0":"key (type: int)"} | outputColumnNames:["_col0","_col1","_col5","_col6"] | Statistics:Num rows: 3 Data size: 28 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_2] | key expressions:key (type: int) | Map-reduce partition columns:key (type: int) | sort order:+ | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE | value expressions:value (type: int) | TableScan [TS_0] | alias:a | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE |<-Map 3 [SIMPLE_EDGE] Reduce Output Operator [RS_3] key expressions:value (type: int) Map-reduce partition columns:value (type: int) sort order:+ Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE value expressions:key (type: int) TableScan [TS_1] alias:b Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: explain select * FROM myinput1 a FULL OUTER JOIN myinput1 b ON a.key<=>b.value PREHOOK: type: QUERY POSTHOOK: query: explain select * FROM myinput1 a FULL OUTER JOIN myinput1 b ON a.key<=>b.value POSTHOOK: type: QUERY Plan not optimized by CBO due to missing feature [Less_than_equal_greater_than]. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_6] compressed:true Statistics:Num rows: 3 Data size: 28 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_5] outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 3 Data size: 28 Basic stats: COMPLETE Column stats: NONE Merge Join Operator [MERGEJOIN_7] | condition map:[{"":"Outer Join 0 to 1"}] | keys:{"1":"value (type: int)","0":"key (type: int)"} | outputColumnNames:["_col0","_col1","_col5","_col6"] | Statistics:Num rows: 3 Data size: 28 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_2] | key expressions:key (type: int) | Map-reduce partition columns:key (type: int) | sort order:+ | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE | value expressions:value (type: int) | TableScan [TS_0] | alias:a | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE |<-Map 3 [SIMPLE_EDGE] Reduce Output Operator [RS_3] key expressions:value (type: int) Map-reduce partition columns:value (type: int) sort order:+ Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE value expressions:key (type: int) TableScan [TS_1] alias:b Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: explain select /*+ MAPJOIN(b) */ * FROM myinput1 a JOIN myinput1 b ON a.key<=>b.value PREHOOK: type: QUERY POSTHOOK: query: explain select /*+ MAPJOIN(b) */ * FROM myinput1 a JOIN myinput1 b ON a.key<=>b.value POSTHOOK: type: QUERY Plan not optimized by CBO due to missing feature [Less_than_equal_greater_than]. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_6] compressed:true Statistics:Num rows: 3 Data size: 28 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_5] outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 3 Data size: 28 Basic stats: COMPLETE Column stats: NONE Merge Join Operator [MERGEJOIN_7] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"1":"value (type: int)","0":"key (type: int)"} | outputColumnNames:["_col0","_col1","_col5","_col6"] | Statistics:Num rows: 3 Data size: 28 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_2] | key expressions:key (type: int) | Map-reduce partition columns:key (type: int) | sort order:+ | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE | value expressions:value (type: int) | TableScan [TS_0] | alias:a | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE |<-Map 3 [SIMPLE_EDGE] Reduce Output Operator [RS_3] key expressions:value (type: int) Map-reduce partition columns:value (type: int) sort order:+ Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE value expressions:key (type: int) TableScan [TS_1] alias:b Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: CREATE TABLE smb_input(key int, value int) PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@smb_input POSTHOOK: query: CREATE TABLE smb_input(key int, value int) POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@smb_input PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/in4.txt' into table smb_input PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@smb_input POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/in4.txt' into table smb_input POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@smb_input PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/in5.txt' into table smb_input PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@smb_input POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/in5.txt' into table smb_input POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@smb_input PREHOOK: query: CREATE TABLE smb_input1(key int, value int) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@smb_input1 POSTHOOK: query: CREATE TABLE smb_input1(key int, value int) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@smb_input1 PREHOOK: query: CREATE TABLE smb_input2(key int, value int) CLUSTERED BY (value) SORTED BY (value) INTO 2 BUCKETS PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@smb_input2 POSTHOOK: query: CREATE TABLE smb_input2(key int, value int) CLUSTERED BY (value) SORTED BY (value) INTO 2 BUCKETS POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@smb_input2 PREHOOK: query: from smb_input insert overwrite table smb_input1 select * insert overwrite table smb_input2 select * PREHOOK: type: QUERY PREHOOK: Input: default@smb_input PREHOOK: Output: default@smb_input1 PREHOOK: Output: default@smb_input2 POSTHOOK: query: from smb_input insert overwrite table smb_input1 select * insert overwrite table smb_input2 select * POSTHOOK: type: QUERY POSTHOOK: Input: default@smb_input POSTHOOK: Output: default@smb_input1 POSTHOOK: Output: default@smb_input2 POSTHOOK: Lineage: smb_input1.key SIMPLE [(smb_input)smb_input.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: smb_input1.value SIMPLE [(smb_input)smb_input.FieldSchema(name:value, type:int, comment:null), ] POSTHOOK: Lineage: smb_input2.key SIMPLE [(smb_input)smb_input.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: smb_input2.value SIMPLE [(smb_input)smb_input.FieldSchema(name:value, type:int, comment:null), ] PREHOOK: query: explain select /*+ MAPJOIN(a) */ * FROM smb_input1 a JOIN smb_input1 b ON a.key <=> b.key PREHOOK: type: QUERY POSTHOOK: query: explain select /*+ MAPJOIN(a) */ * FROM smb_input1 a JOIN smb_input1 b ON a.key <=> b.key POSTHOOK: type: QUERY Plan not optimized by CBO due to missing feature [Less_than_equal_greater_than]. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_6] compressed:true Statistics:Num rows: 28 Data size: 209 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_5] outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 28 Data size: 209 Basic stats: COMPLETE Column stats: NONE Merge Join Operator [MERGEJOIN_7] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"1":"key (type: int)","0":"key (type: int)"} | outputColumnNames:["_col0","_col1","_col5","_col6"] | Statistics:Num rows: 28 Data size: 209 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_2] | key expressions:key (type: int) | Map-reduce partition columns:key (type: int) | sort order:+ | Statistics:Num rows: 26 Data size: 190 Basic stats: COMPLETE Column stats: NONE | value expressions:value (type: int) | TableScan [TS_0] | alias:a | Statistics:Num rows: 26 Data size: 190 Basic stats: COMPLETE Column stats: NONE |<-Map 3 [SIMPLE_EDGE] Reduce Output Operator [RS_3] key expressions:key (type: int) Map-reduce partition columns:key (type: int) sort order:+ Statistics:Num rows: 26 Data size: 190 Basic stats: COMPLETE Column stats: NONE value expressions:value (type: int) TableScan [TS_1] alias:b Statistics:Num rows: 26 Data size: 190 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: explain select /*+ MAPJOIN(a) */ * FROM smb_input1 a JOIN smb_input1 b ON a.key <=> b.key AND a.value <=> b.value PREHOOK: type: QUERY POSTHOOK: query: explain select /*+ MAPJOIN(a) */ * FROM smb_input1 a JOIN smb_input1 b ON a.key <=> b.key AND a.value <=> b.value POSTHOOK: type: QUERY Plan not optimized by CBO due to missing feature [Less_than_equal_greater_than]. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_6] compressed:true Statistics:Num rows: 28 Data size: 209 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_5] outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 28 Data size: 209 Basic stats: COMPLETE Column stats: NONE Merge Join Operator [MERGEJOIN_7] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"1":"key (type: int), value (type: int)","0":"key (type: int), value (type: int)"} | outputColumnNames:["_col0","_col1","_col5","_col6"] | Statistics:Num rows: 28 Data size: 209 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_2] | key expressions:key (type: int), value (type: int) | Map-reduce partition columns:key (type: int), value (type: int) | sort order:++ | Statistics:Num rows: 26 Data size: 190 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_0] | alias:a | Statistics:Num rows: 26 Data size: 190 Basic stats: COMPLETE Column stats: NONE |<-Map 3 [SIMPLE_EDGE] Reduce Output Operator [RS_3] key expressions:key (type: int), value (type: int) Map-reduce partition columns:key (type: int), value (type: int) sort order:++ Statistics:Num rows: 26 Data size: 190 Basic stats: COMPLETE Column stats: NONE TableScan [TS_1] alias:b Statistics:Num rows: 26 Data size: 190 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: explain select /*+ MAPJOIN(a) */ * FROM smb_input1 a RIGHT OUTER JOIN smb_input1 b ON a.key <=> b.key PREHOOK: type: QUERY POSTHOOK: query: explain select /*+ MAPJOIN(a) */ * FROM smb_input1 a RIGHT OUTER JOIN smb_input1 b ON a.key <=> b.key POSTHOOK: type: QUERY Plan not optimized by CBO due to missing feature [Less_than_equal_greater_than]. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_6] compressed:true Statistics:Num rows: 28 Data size: 209 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_5] outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 28 Data size: 209 Basic stats: COMPLETE Column stats: NONE Merge Join Operator [MERGEJOIN_7] | condition map:[{"":"Right Outer Join0 to 1"}] | keys:{"1":"key (type: int)","0":"key (type: int)"} | outputColumnNames:["_col0","_col1","_col5","_col6"] | Statistics:Num rows: 28 Data size: 209 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_2] | key expressions:key (type: int) | Map-reduce partition columns:key (type: int) | sort order:+ | Statistics:Num rows: 26 Data size: 190 Basic stats: COMPLETE Column stats: NONE | value expressions:value (type: int) | TableScan [TS_0] | alias:a | Statistics:Num rows: 26 Data size: 190 Basic stats: COMPLETE Column stats: NONE |<-Map 3 [SIMPLE_EDGE] Reduce Output Operator [RS_3] key expressions:key (type: int) Map-reduce partition columns:key (type: int) sort order:+ Statistics:Num rows: 26 Data size: 190 Basic stats: COMPLETE Column stats: NONE value expressions:value (type: int) TableScan [TS_1] alias:b Statistics:Num rows: 26 Data size: 190 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: explain select /*+ MAPJOIN(b) */ * FROM smb_input1 a JOIN smb_input1 b ON a.key <=> b.key PREHOOK: type: QUERY POSTHOOK: query: explain select /*+ MAPJOIN(b) */ * FROM smb_input1 a JOIN smb_input1 b ON a.key <=> b.key POSTHOOK: type: QUERY Plan not optimized by CBO due to missing feature [Less_than_equal_greater_than]. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_6] compressed:true Statistics:Num rows: 28 Data size: 209 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_5] outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 28 Data size: 209 Basic stats: COMPLETE Column stats: NONE Merge Join Operator [MERGEJOIN_7] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"1":"key (type: int)","0":"key (type: int)"} | outputColumnNames:["_col0","_col1","_col5","_col6"] | Statistics:Num rows: 28 Data size: 209 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_2] | key expressions:key (type: int) | Map-reduce partition columns:key (type: int) | sort order:+ | Statistics:Num rows: 26 Data size: 190 Basic stats: COMPLETE Column stats: NONE | value expressions:value (type: int) | TableScan [TS_0] | alias:a | Statistics:Num rows: 26 Data size: 190 Basic stats: COMPLETE Column stats: NONE |<-Map 3 [SIMPLE_EDGE] Reduce Output Operator [RS_3] key expressions:key (type: int) Map-reduce partition columns:key (type: int) sort order:+ Statistics:Num rows: 26 Data size: 190 Basic stats: COMPLETE Column stats: NONE value expressions:value (type: int) TableScan [TS_1] alias:b Statistics:Num rows: 26 Data size: 190 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: explain select /*+ MAPJOIN(b) */ * FROM smb_input1 a LEFT OUTER JOIN smb_input1 b ON a.key <=> b.key PREHOOK: type: QUERY POSTHOOK: query: explain select /*+ MAPJOIN(b) */ * FROM smb_input1 a LEFT OUTER JOIN smb_input1 b ON a.key <=> b.key POSTHOOK: type: QUERY Plan not optimized by CBO due to missing feature [Less_than_equal_greater_than]. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_6] compressed:true Statistics:Num rows: 28 Data size: 209 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_5] outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 28 Data size: 209 Basic stats: COMPLETE Column stats: NONE Merge Join Operator [MERGEJOIN_7] | condition map:[{"":"Left Outer Join0 to 1"}] | keys:{"1":"key (type: int)","0":"key (type: int)"} | outputColumnNames:["_col0","_col1","_col5","_col6"] | Statistics:Num rows: 28 Data size: 209 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_2] | key expressions:key (type: int) | Map-reduce partition columns:key (type: int) | sort order:+ | Statistics:Num rows: 26 Data size: 190 Basic stats: COMPLETE Column stats: NONE | value expressions:value (type: int) | TableScan [TS_0] | alias:a | Statistics:Num rows: 26 Data size: 190 Basic stats: COMPLETE Column stats: NONE |<-Map 3 [SIMPLE_EDGE] Reduce Output Operator [RS_3] key expressions:key (type: int) Map-reduce partition columns:key (type: int) sort order:+ Statistics:Num rows: 26 Data size: 190 Basic stats: COMPLETE Column stats: NONE value expressions:value (type: int) TableScan [TS_1] alias:b Statistics:Num rows: 26 Data size: 190 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: drop table sales PREHOOK: type: DROPTABLE POSTHOOK: query: drop table sales POSTHOOK: type: DROPTABLE PREHOOK: query: drop table things PREHOOK: type: DROPTABLE POSTHOOK: query: drop table things POSTHOOK: type: DROPTABLE PREHOOK: query: CREATE TABLE sales (name STRING, id INT) ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@sales POSTHOOK: query: CREATE TABLE sales (name STRING, id INT) ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@sales PREHOOK: query: CREATE TABLE things (id INT, name STRING) partitioned by (ds string) ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@things POSTHOOK: query: CREATE TABLE things (id INT, name STRING) partitioned by (ds string) ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@things PREHOOK: query: load data local inpath '../../data/files/sales.txt' INTO TABLE sales PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@sales POSTHOOK: query: load data local inpath '../../data/files/sales.txt' INTO TABLE sales POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@sales PREHOOK: query: load data local inpath '../../data/files/things.txt' INTO TABLE things partition(ds='2011-10-23') PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@things POSTHOOK: query: load data local inpath '../../data/files/things.txt' INTO TABLE things partition(ds='2011-10-23') POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@things POSTHOOK: Output: default@things@ds=2011-10-23 PREHOOK: query: load data local inpath '../../data/files/things2.txt' INTO TABLE things partition(ds='2011-10-24') PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@things POSTHOOK: query: load data local inpath '../../data/files/things2.txt' INTO TABLE things partition(ds='2011-10-24') POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@things POSTHOOK: Output: default@things@ds=2011-10-24 PREHOOK: query: explain select name,id FROM sales LEFT SEMI JOIN things ON (sales.id = things.id) PREHOOK: type: QUERY POSTHOOK: query: explain select name,id FROM sales LEFT SEMI JOIN things ON (sales.id = things.id) POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_12] compressed:true Statistics:Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Merge Join Operator [MERGEJOIN_17] | condition map:[{"":"Left Semi Join 0 to 1"}] | keys:{"1":"_col0 (type: int)","0":"_col1 (type: int)"} | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_7] | key expressions:_col1 (type: int) | Map-reduce partition columns:_col1 (type: int) | sort order:+ | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE | value expressions:_col0 (type: string) | Select Operator [SEL_1] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE | Filter Operator [FIL_15] | predicate:id is not null (type: boolean) | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE | TableScan [TS_0] | alias:sales | Statistics:Num rows: 0 Data size: 13 Basic stats: PARTIAL Column stats: NONE |<-Map 3 [SIMPLE_EDGE] Reduce Output Operator [RS_9] key expressions:_col0 (type: int) Map-reduce partition columns:_col0 (type: int) sort order:+ Statistics:Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE Group By Operator [GBY_5] keys:_col0 (type: int) outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE Select Operator [SEL_3] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE Filter Operator [FIL_16] predicate:id is not null (type: boolean) Statistics:Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE TableScan [TS_2] alias:things Statistics:Num rows: 2 Data size: 12 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: drop table sales PREHOOK: type: DROPTABLE PREHOOK: Input: default@sales PREHOOK: Output: default@sales POSTHOOK: query: drop table sales POSTHOOK: type: DROPTABLE POSTHOOK: Input: default@sales POSTHOOK: Output: default@sales PREHOOK: query: drop table things PREHOOK: type: DROPTABLE PREHOOK: Input: default@things PREHOOK: Output: default@things POSTHOOK: query: drop table things POSTHOOK: type: DROPTABLE POSTHOOK: Input: default@things POSTHOOK: Output: default@things PREHOOK: query: explain select srcpart.key from srcpart join src on (srcpart.value=src.value) join src1 on (srcpart.key=src1.key) where srcpart.value > 'val_450' PREHOOK: type: QUERY POSTHOOK: query: explain select srcpart.key from srcpart join src on (srcpart.value=src.value) join src1 on (srcpart.key=src1.key) where srcpart.value > 'val_450' POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) Map 3 <- Map 4 (BROADCAST_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_20] compressed:true Statistics:Num rows: 555 Data size: 48285 Basic stats: COMPLETE Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_19] outputColumnNames:["_col0"] Statistics:Num rows: 555 Data size: 48285 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator [MERGEJOIN_30] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"1":"_col1 (type: string)","0":"_col0 (type: string)"} | outputColumnNames:["_col1"] | Statistics:Num rows: 555 Data size: 48285 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_15] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 166 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_2] | outputColumnNames:["_col0"] | Statistics:Num rows: 166 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_26] | predicate:(value > 'val_450') (type: boolean) | Statistics:Num rows: 166 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:src | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 3 [SIMPLE_EDGE] Reduce Output Operator [RS_17] key expressions:_col1 (type: string) Map-reduce partition columns:_col1 (type: string) sort order:+ Statistics:Num rows: 241 Data size: 42898 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: string) Map Join Operator [MAPJOIN_29] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"Map 3":"_col0 (type: string)","Map 4":"_col0 (type: string)"} | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 241 Data size: 42898 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 4 [BROADCAST_EDGE] | Reduce Output Operator [RS_11] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_7] | outputColumnNames:["_col0"] | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_28] | predicate:key is not null (type: boolean) | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_6] | alias:src1 | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE |<-Select Operator [SEL_5] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 666 Data size: 118548 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator [FIL_27] predicate:(((value > 'val_450') and key is not null) and value is not null) (type: boolean) Statistics:Num rows: 666 Data size: 118548 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_3] alias:srcpart Statistics:Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select srcpart.key from srcpart join src on (srcpart.value=src.value) join src1 on (srcpart.key=src1.key) where srcpart.value > 'val_450' PREHOOK: type: QUERY POSTHOOK: query: explain select srcpart.key from srcpart join src on (srcpart.value=src.value) join src1 on (srcpart.key=src1.key) where srcpart.value > 'val_450' POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) Map 3 <- Map 4 (BROADCAST_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_20] compressed:true Statistics:Num rows: 555 Data size: 48285 Basic stats: COMPLETE Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_19] outputColumnNames:["_col0"] Statistics:Num rows: 555 Data size: 48285 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator [MERGEJOIN_30] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"1":"_col1 (type: string)","0":"_col0 (type: string)"} | outputColumnNames:["_col1"] | Statistics:Num rows: 555 Data size: 48285 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_15] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 166 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_2] | outputColumnNames:["_col0"] | Statistics:Num rows: 166 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_26] | predicate:(value > 'val_450') (type: boolean) | Statistics:Num rows: 166 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:src | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 3 [SIMPLE_EDGE] Reduce Output Operator [RS_17] key expressions:_col1 (type: string) Map-reduce partition columns:_col1 (type: string) sort order:+ Statistics:Num rows: 241 Data size: 42898 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: string) Map Join Operator [MAPJOIN_29] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"Map 3":"_col0 (type: string)","Map 4":"_col0 (type: string)"} | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 241 Data size: 42898 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 4 [BROADCAST_EDGE] | Reduce Output Operator [RS_11] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_7] | outputColumnNames:["_col0"] | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_28] | predicate:key is not null (type: boolean) | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_6] | alias:src1 | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE |<-Select Operator [SEL_5] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 666 Data size: 118548 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator [FIL_27] predicate:(((value > 'val_450') and key is not null) and value is not null) (type: boolean) Statistics:Num rows: 666 Data size: 118548 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_3] alias:srcpart Statistics:Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select srcpart.key from srcpart join src on (srcpart.value=src.value) join src1 on (srcpart.key=src1.key) where srcpart.value > 'val_450' PREHOOK: type: QUERY POSTHOOK: query: explain select srcpart.key from srcpart join src on (srcpart.value=src.value) join src1 on (srcpart.key=src1.key) where srcpart.value > 'val_450' POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) Map 3 <- Map 4 (BROADCAST_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_20] compressed:true Statistics:Num rows: 555 Data size: 48285 Basic stats: COMPLETE Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_19] outputColumnNames:["_col0"] Statistics:Num rows: 555 Data size: 48285 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator [MERGEJOIN_30] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"1":"_col1 (type: string)","0":"_col0 (type: string)"} | outputColumnNames:["_col1"] | Statistics:Num rows: 555 Data size: 48285 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_15] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 166 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_2] | outputColumnNames:["_col0"] | Statistics:Num rows: 166 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_26] | predicate:(value > 'val_450') (type: boolean) | Statistics:Num rows: 166 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:src | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 3 [SIMPLE_EDGE] Reduce Output Operator [RS_17] key expressions:_col1 (type: string) Map-reduce partition columns:_col1 (type: string) sort order:+ Statistics:Num rows: 241 Data size: 42898 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: string) Map Join Operator [MAPJOIN_29] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"Map 3":"_col0 (type: string)","Map 4":"_col0 (type: string)"} | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 241 Data size: 42898 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 4 [BROADCAST_EDGE] | Reduce Output Operator [RS_11] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_7] | outputColumnNames:["_col0"] | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_28] | predicate:key is not null (type: boolean) | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_6] | alias:src1 | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE |<-Select Operator [SEL_5] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 666 Data size: 118548 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator [FIL_27] predicate:(((value > 'val_450') and key is not null) and value is not null) (type: boolean) Statistics:Num rows: 666 Data size: 118548 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_3] alias:srcpart Statistics:Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 from noop(on part partition by p_mfgr order by p_name ) PREHOOK: type: QUERY POSTHOOK: query: explain select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 from noop(on part partition by p_mfgr order by p_name ) POSTHOOK: type: QUERY Plan not optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 3 File Output Operator [FS_9] compressed:true Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_7] outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE PTF Operator [PTF_6] Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"_col2","name:":"windowingtablefunction","order by:":"_col1"}] Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator [SEL_5] | outputColumnNames:["_col1","_col2","_col5","_col7"] | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_4] key expressions:_col2 (type: string), _col1 (type: string) Map-reduce partition columns:_col2 (type: string) sort order:++ Statistics:Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col5 (type: int), _col7 (type: double) PTF Operator [PTF_3] Function definitions:[{"Input definition":{"type:":"TABLE"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col1"}}] Statistics:Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_2] | outputColumnNames:["_col1","_col2","_col5","_col7"] | Statistics:Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_1] key expressions:p_mfgr (type: string), p_name (type: string) Map-reduce partition columns:p_mfgr (type: string) sort order:++ Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE value expressions:p_size (type: int), p_retailprice (type: double) TableScan [TS_0] alias:part Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select p_mfgr, p_name, p_size, p_size - lag(p_size,1,p_size) over (partition by p_mfgr order by p_name) as deltaSz from noop (on (select p1.* from part p1 join part p2 on p1.p_partkey = p2.p_partkey) j distribute by j.p_mfgr sort by j.p_name) PREHOOK: type: QUERY POSTHOOK: query: explain select p_mfgr, p_name, p_size, p_size - lag(p_size,1,p_size) over (partition by p_mfgr order by p_name) as deltaSz from noop (on (select p1.* from part p1 join part p2 on p1.p_partkey = p2.p_partkey) j distribute by j.p_mfgr sort by j.p_name) POSTHOOK: type: QUERY Plan not optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Map 1 <- Map 4 (BROADCAST_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 3 File Output Operator [FS_16] compressed:true Statistics:Num rows: 29 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_14] outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 29 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE PTF Operator [PTF_13] Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"_col2","name:":"windowingtablefunction","order by:":"_col1"}] Statistics:Num rows: 29 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator [SEL_12] | outputColumnNames:["_col1","_col2","_col5"] | Statistics:Num rows: 29 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_11] key expressions:_col2 (type: string), _col1 (type: string) Map-reduce partition columns:_col2 (type: string) sort order:++ Statistics:Num rows: 29 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE value expressions:_col5 (type: int) PTF Operator [PTF_10] Function definitions:[{"Input definition":{"type:":"SUBQUERY"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col1"}}] Statistics:Num rows: 29 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator [SEL_9] | outputColumnNames:["_col1","_col2","_col5"] | Statistics:Num rows: 29 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_8] key expressions:_col2 (type: string), _col1 (type: string) Map-reduce partition columns:_col2 (type: string) sort order:++ Statistics:Num rows: 29 Data size: 6467 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col5 (type: int) Map Join Operator [MAPJOIN_21] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"Map 1":"p_partkey (type: int)","Map 4":"p_partkey (type: int)"} | outputColumnNames:["_col1","_col2","_col5"] | Statistics:Num rows: 29 Data size: 6467 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 4 [BROADCAST_EDGE] | Reduce Output Operator [RS_5] | key expressions:p_partkey (type: int) | Map-reduce partition columns:p_partkey (type: int) | sort order:+ | Statistics:Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_20] | predicate:p_partkey is not null (type: boolean) | Statistics:Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_1] | alias:p2 | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE |<-Filter Operator [FIL_19] predicate:p_partkey is not null (type: boolean) Statistics:Num rows: 26 Data size: 5902 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_0] alias:p1 Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 from noop(on part partition by p_mfgr order by p_name ) abc PREHOOK: type: QUERY POSTHOOK: query: explain select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 from noop(on part partition by p_mfgr order by p_name ) abc POSTHOOK: type: QUERY Plan not optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 3 File Output Operator [FS_9] compressed:true Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_7] outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE PTF Operator [PTF_6] Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"_col2","name:":"windowingtablefunction","order by:":"_col1"}] Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator [SEL_5] | outputColumnNames:["_col1","_col2","_col5","_col7"] | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_4] key expressions:_col2 (type: string), _col1 (type: string) Map-reduce partition columns:_col2 (type: string) sort order:++ Statistics:Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col5 (type: int), _col7 (type: double) PTF Operator [PTF_3] Function definitions:[{"Input definition":{"type:":"TABLE"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col1"}}] Statistics:Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_2] | outputColumnNames:["_col1","_col2","_col5","_col7"] | Statistics:Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_1] key expressions:p_mfgr (type: string), p_name (type: string) Map-reduce partition columns:p_mfgr (type: string) sort order:++ Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE value expressions:p_size (type: int), p_retailprice (type: double) TableScan [TS_0] alias:part Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, p_size, p_size - lag(p_size,1,p_size) over (partition by p_mfgr order by p_name) as deltaSz from noop(on part partition by p_mfgr order by p_name ) PREHOOK: type: QUERY POSTHOOK: query: explain select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, p_size, p_size - lag(p_size,1,p_size) over (partition by p_mfgr order by p_name) as deltaSz from noop(on part partition by p_mfgr order by p_name ) POSTHOOK: type: QUERY Plan not optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 3 File Output Operator [FS_9] compressed:true Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_7] outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE PTF Operator [PTF_6] Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"_col2","name:":"windowingtablefunction","order by:":"_col1"}] Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator [SEL_5] | outputColumnNames:["_col1","_col2","_col5"] | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_4] key expressions:_col2 (type: string), _col1 (type: string) Map-reduce partition columns:_col2 (type: string) sort order:++ Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col5 (type: int) PTF Operator [PTF_3] Function definitions:[{"Input definition":{"type:":"TABLE"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col1"}}] Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_2] | outputColumnNames:["_col1","_col2","_col5"] | Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_1] key expressions:p_mfgr (type: string), p_name (type: string) Map-reduce partition columns:p_mfgr (type: string) sort order:++ Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE value expressions:p_size (type: int) TableScan [TS_0] alias:part Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, p_size, p_size - lag(p_size,1,p_size) over (partition by p_mfgr order by p_name) as deltaSz from noop(on part partition by p_mfgr order by p_name ) group by p_mfgr, p_name, p_size PREHOOK: type: QUERY POSTHOOK: query: explain select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, p_size, p_size - lag(p_size,1,p_size) over (partition by p_mfgr order by p_name) as deltaSz from noop(on part partition by p_mfgr order by p_name ) group by p_mfgr, p_name, p_size POSTHOOK: type: QUERY Plan not optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Reducer 5 <- Reducer 4 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 5 File Output Operator [FS_14] compressed:true Statistics:Num rows: 13 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_12] outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] Statistics:Num rows: 13 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE PTF Operator [PTF_11] Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"_col0","name:":"windowingtablefunction","order by:":"_col1"}] Statistics:Num rows: 13 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator [SEL_10] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 13 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE |<-Reducer 4 [SIMPLE_EDGE] Reduce Output Operator [RS_9] key expressions:_col0 (type: string), _col1 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:++ Statistics:Num rows: 13 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE value expressions:_col2 (type: int) Group By Operator [GBY_8] | keys:KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int) | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 13 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE |<-Reducer 3 [SIMPLE_EDGE] Reduce Output Operator [RS_7] key expressions:_col0 (type: string), _col1 (type: string), _col2 (type: int) Map-reduce partition columns:_col0 (type: string), _col1 (type: string), _col2 (type: int) sort order:+++ Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Group By Operator [GBY_6] | keys:KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int) | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_5] key expressions:_col2 (type: string), _col1 (type: string), _col5 (type: int) Map-reduce partition columns:rand() (type: double) sort order:+++ Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator [PTF_3] Function definitions:[{"Input definition":{"type:":"TABLE"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col1"}}] Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_2] | outputColumnNames:["_col1","_col2","_col5"] | Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_1] key expressions:p_mfgr (type: string), p_name (type: string) Map-reduce partition columns:p_mfgr (type: string) sort order:++ Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE value expressions:p_size (type: int) TableScan [TS_0] alias:part Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select abc.* from noop(on part partition by p_mfgr order by p_name ) abc join part p1 on abc.p_partkey = p1.p_partkey PREHOOK: type: QUERY POSTHOOK: query: explain select abc.* from noop(on part partition by p_mfgr order by p_name ) abc join part p1 on abc.p_partkey = p1.p_partkey POSTHOOK: type: QUERY Plan not optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (BROADCAST_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_11] compressed:true Statistics:Num rows: 14 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Map Join Operator [MAPJOIN_16] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"Reducer 2":"_col0 (type: int)","Map 3":"p_partkey (type: int)"} | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] | Statistics:Num rows: 14 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE |<-Map 3 [BROADCAST_EDGE] | Reduce Output Operator [RS_8] | key expressions:p_partkey (type: int) | Map-reduce partition columns:p_partkey (type: int) | sort order:+ | Statistics:Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_15] | predicate:p_partkey is not null (type: boolean) | Statistics:Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_1] | alias:p1 | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE |<-Filter Operator [FIL_14] predicate:_col0 is not null (type: boolean) Statistics:Num rows: 13 Data size: 8047 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator [PTF_4] Function definitions:[{"Input definition":{"type:":"TABLE"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col1"}}] Statistics:Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_3] | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] | Statistics:Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_2] key expressions:p_mfgr (type: string), p_name (type: string) Map-reduce partition columns:p_mfgr (type: string) sort order:++ Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE value expressions:p_partkey (type: int), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) TableScan [TS_0] alias:part Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name, p_size desc) as r from noopwithmap(on part partition by p_mfgr order by p_name, p_size desc) PREHOOK: type: QUERY POSTHOOK: query: explain select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name, p_size desc) as r from noopwithmap(on part partition by p_mfgr order by p_name, p_size desc) POSTHOOK: type: QUERY Plan not optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 3 File Output Operator [FS_10] compressed:true Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_8] outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE PTF Operator [PTF_7] Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"_col2","name:":"windowingtablefunction","order by:":"_col1, _col5(DESC)"}] Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator [SEL_6] | outputColumnNames:["_col1","_col2","_col5"] | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_5] key expressions:_col2 (type: string), _col1 (type: string), _col5 (type: int) Map-reduce partition columns:_col2 (type: string) sort order:++- Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE PTF Operator [PTF_4] Function definitions:[{"Input definition":{"type:":"TABLE"}},{"Partition table definition":{"partition by:":"_col2","name:":"noopwithmap","order by:":"_col1, _col5(DESC)"}}] Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator [SEL_3] | outputColumnNames:["_col1","_col2","_col5"] | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_2] key expressions:p_mfgr (type: string), p_name (type: string), p_size (type: int) Map-reduce partition columns:p_mfgr (type: string) sort order:++- Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator [PTF_1] Function definitions:[{"Input definition":{"type:":"TABLE"}},{"Partition table definition":{"partition by:":"p_mfgr","name:":"noopwithmap","order by:":"p_name, p_size(DESC)"}}] Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_0] alias:part Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 from noopwithmap(on part partition by p_mfgr order by p_name) PREHOOK: type: QUERY POSTHOOK: query: explain select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 from noopwithmap(on part partition by p_mfgr order by p_name) POSTHOOK: type: QUERY Plan not optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 3 File Output Operator [FS_10] compressed:true Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_8] outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE PTF Operator [PTF_7] Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"_col2","name:":"windowingtablefunction","order by:":"_col1"}] Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator [SEL_6] | outputColumnNames:["_col1","_col2","_col5","_col7"] | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_5] key expressions:_col2 (type: string), _col1 (type: string) Map-reduce partition columns:_col2 (type: string) sort order:++ Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE value expressions:_col5 (type: int), _col7 (type: double) PTF Operator [PTF_4] Function definitions:[{"Input definition":{"type:":"TABLE"}},{"Partition table definition":{"partition by:":"_col2","name:":"noopwithmap","order by:":"_col1"}}] Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator [SEL_3] | outputColumnNames:["_col1","_col2","_col5","_col7"] | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_2] key expressions:p_mfgr (type: string), p_name (type: string) Map-reduce partition columns:p_mfgr (type: string) sort order:++ Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE value expressions:p_size (type: int), p_retailprice (type: double) PTF Operator [PTF_1] Function definitions:[{"Input definition":{"type:":"TABLE"}},{"Partition table definition":{"partition by:":"p_mfgr","name:":"noopwithmap","order by:":"p_name"}}] Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_0] alias:part Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 from noop(on part partition by p_mfgr order by p_name) PREHOOK: type: QUERY POSTHOOK: query: explain select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 from noop(on part partition by p_mfgr order by p_name) POSTHOOK: type: QUERY Plan not optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 3 File Output Operator [FS_9] compressed:true Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_7] outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE PTF Operator [PTF_6] Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"_col2","name:":"windowingtablefunction","order by:":"_col1"}] Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator [SEL_5] | outputColumnNames:["_col1","_col2","_col5","_col7"] | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_4] key expressions:_col2 (type: string), _col1 (type: string) Map-reduce partition columns:_col2 (type: string) sort order:++ Statistics:Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col5 (type: int), _col7 (type: double) PTF Operator [PTF_3] Function definitions:[{"Input definition":{"type:":"TABLE"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col1"}}] Statistics:Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_2] | outputColumnNames:["_col1","_col2","_col5","_col7"] | Statistics:Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_1] key expressions:p_mfgr (type: string), p_name (type: string) Map-reduce partition columns:p_mfgr (type: string) sort order:++ Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE value expressions:p_size (type: int), p_retailprice (type: double) TableScan [TS_0] alias:part Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 from noop(on noopwithmap(on noop(on part partition by p_mfgr order by p_mfgr DESC, p_name ))) PREHOOK: type: QUERY POSTHOOK: query: explain select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 from noop(on noopwithmap(on noop(on part partition by p_mfgr order by p_mfgr DESC, p_name ))) POSTHOOK: type: QUERY Plan not optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 4 File Output Operator [FS_13] compressed:true Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_11] outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE PTF Operator [PTF_10] Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"_col2","name:":"windowingtablefunction","order by:":"_col1"}] Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator [SEL_9] | outputColumnNames:["_col1","_col2","_col5","_col7"] | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE |<-Reducer 3 [SIMPLE_EDGE] Reduce Output Operator [RS_8] key expressions:_col2 (type: string), _col1 (type: string) Map-reduce partition columns:_col2 (type: string) sort order:++ Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE value expressions:_col5 (type: int), _col7 (type: double) PTF Operator [PTF_7] Function definitions:[{"Input definition":{"type:":"PTFCOMPONENT"}},{"Partition table definition":{"partition by:":"_col2","name:":"noopwithmap","order by:":"_col2(DESC), _col1"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col2(DESC), _col1"}}] Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator [SEL_6] | outputColumnNames:["_col1","_col2","_col5","_col7"] | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_5] key expressions:_col2 (type: string), _col1 (type: string) Map-reduce partition columns:_col2 (type: string) sort order:-+ Statistics:Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col5 (type: int), _col7 (type: double) PTF Operator [PTF_4] Function definitions:[{"Input definition":{"type:":"PTFCOMPONENT"}},{"Partition table definition":{"partition by:":"_col2","name:":"noopwithmap","order by:":"_col2(DESC), _col1"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col2(DESC), _col1"}}] Statistics:Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator [PTF_3] Function definitions:[{"Input definition":{"type:":"TABLE"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col2(DESC), _col1"}}] Statistics:Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_2] | outputColumnNames:["_col1","_col2","_col5","_col7"] | Statistics:Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_1] key expressions:p_mfgr (type: string), p_name (type: string) Map-reduce partition columns:p_mfgr (type: string) sort order:-+ Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE value expressions:p_size (type: int), p_retailprice (type: double) TableScan [TS_0] alias:part Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select p_mfgr, p_name, sub1.cd, sub1.s1 from (select p_mfgr, p_name, count(p_size) over (partition by p_mfgr order by p_name) as cd, p_retailprice, sum(p_retailprice) over w1 as s1 from noop(on part partition by p_mfgr order by p_name) window w1 as (partition by p_mfgr order by p_name rows between 2 preceding and 2 following) ) sub1 PREHOOK: type: QUERY POSTHOOK: query: explain select p_mfgr, p_name, sub1.cd, sub1.s1 from (select p_mfgr, p_name, count(p_size) over (partition by p_mfgr order by p_name) as cd, p_retailprice, sum(p_retailprice) over w1 as s1 from noop(on part partition by p_mfgr order by p_name) window w1 as (partition by p_mfgr order by p_name rows between 2 preceding and 2 following) ) sub1 POSTHOOK: type: QUERY Plan not optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 3 File Output Operator [FS_10] compressed:true Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_7] outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE PTF Operator [PTF_6] Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"_col2","name:":"windowingtablefunction","order by:":"_col1"}] Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator [SEL_5] | outputColumnNames:["_col1","_col2","_col5","_col7"] | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_4] key expressions:_col2 (type: string), _col1 (type: string) Map-reduce partition columns:_col2 (type: string) sort order:++ Statistics:Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col5 (type: int), _col7 (type: double) PTF Operator [PTF_3] Function definitions:[{"Input definition":{"type:":"TABLE"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col1"}}] Statistics:Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_2] | outputColumnNames:["_col1","_col2","_col5","_col7"] | Statistics:Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_1] key expressions:p_mfgr (type: string), p_name (type: string) Map-reduce partition columns:p_mfgr (type: string) sort order:++ Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE value expressions:p_size (type: int), p_retailprice (type: double) TableScan [TS_0] alias:part Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select abc.p_mfgr, abc.p_name, rank() over (distribute by abc.p_mfgr sort by abc.p_name) as r, dense_rank() over (distribute by abc.p_mfgr sort by abc.p_name) as dr, count(abc.p_name) over (distribute by abc.p_mfgr sort by abc.p_name) as cd, abc.p_retailprice, sum(abc.p_retailprice) over (distribute by abc.p_mfgr sort by abc.p_name rows between unbounded preceding and current row) as s1, abc.p_size, abc.p_size - lag(abc.p_size,1,abc.p_size) over (distribute by abc.p_mfgr sort by abc.p_name) as deltaSz from noop(on part partition by p_mfgr order by p_name ) abc join part p1 on abc.p_partkey = p1.p_partkey PREHOOK: type: QUERY POSTHOOK: query: explain select abc.p_mfgr, abc.p_name, rank() over (distribute by abc.p_mfgr sort by abc.p_name) as r, dense_rank() over (distribute by abc.p_mfgr sort by abc.p_name) as dr, count(abc.p_name) over (distribute by abc.p_mfgr sort by abc.p_name) as cd, abc.p_retailprice, sum(abc.p_retailprice) over (distribute by abc.p_mfgr sort by abc.p_name rows between unbounded preceding and current row) as s1, abc.p_size, abc.p_size - lag(abc.p_size,1,abc.p_size) over (distribute by abc.p_mfgr sort by abc.p_name) as deltaSz from noop(on part partition by p_mfgr order by p_name ) abc join part p1 on abc.p_partkey = p1.p_partkey POSTHOOK: type: QUERY Plan not optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (BROADCAST_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 3 File Output Operator [FS_15] compressed:true Statistics:Num rows: 14 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_13] outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] Statistics:Num rows: 14 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE PTF Operator [PTF_12] Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"_col2","name:":"windowingtablefunction","order by:":"_col1"}] Statistics:Num rows: 14 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator [SEL_11] | outputColumnNames:["_col1","_col2","_col5","_col7"] | Statistics:Num rows: 14 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_10] key expressions:_col2 (type: string), _col1 (type: string) Map-reduce partition columns:_col2 (type: string) sort order:++ Statistics:Num rows: 14 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE value expressions:_col5 (type: int), _col7 (type: double) Map Join Operator [MAPJOIN_20] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"Reducer 2":"_col0 (type: int)","Map 4":"p_partkey (type: int)"} | outputColumnNames:["_col1","_col2","_col5","_col7"] | Statistics:Num rows: 14 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE |<-Map 4 [BROADCAST_EDGE] | Reduce Output Operator [RS_8] | key expressions:p_partkey (type: int) | Map-reduce partition columns:p_partkey (type: int) | sort order:+ | Statistics:Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_19] | predicate:p_partkey is not null (type: boolean) | Statistics:Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_1] | alias:p1 | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE |<-Filter Operator [FIL_18] predicate:_col0 is not null (type: boolean) Statistics:Num rows: 13 Data size: 3055 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator [PTF_4] Function definitions:[{"Input definition":{"type:":"TABLE"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col1"}}] Statistics:Num rows: 26 Data size: 6110 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_3] | outputColumnNames:["_col0","_col1","_col2","_col5","_col7"] | Statistics:Num rows: 26 Data size: 6110 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_2] key expressions:p_mfgr (type: string), p_name (type: string) Map-reduce partition columns:p_mfgr (type: string) sort order:++ Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE value expressions:p_partkey (type: int), p_size (type: int), p_retailprice (type: double) TableScan [TS_0] alias:part Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain create view IF NOT EXISTS mfgr_price_view as select p_mfgr, p_brand, sum(p_retailprice) as s from part group by p_mfgr, p_brand PREHOOK: type: CREATEVIEW POSTHOOK: query: explain create view IF NOT EXISTS mfgr_price_view as select p_mfgr, p_brand, sum(p_retailprice) as s from part group by p_mfgr, p_brand POSTHOOK: type: CREATEVIEW Plan not optimized by CBO. Stage-0 Create View Operator: name:default.mfgr_price_view original text:select p_mfgr, p_brand, sum(p_retailprice) as s from part group by p_mfgr, p_brand PREHOOK: query: CREATE TABLE part_4( p_mfgr STRING, p_name STRING, p_size INT, r INT, dr INT, s DOUBLE) PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@part_4 POSTHOOK: query: CREATE TABLE part_4( p_mfgr STRING, p_name STRING, p_size INT, r INT, dr INT, s DOUBLE) POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@part_4 PREHOOK: query: CREATE TABLE part_5( p_mfgr STRING, p_name STRING, p_size INT, s2 INT, r INT, dr INT, cud DOUBLE, fv1 INT) PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@part_5 POSTHOOK: query: CREATE TABLE part_5( p_mfgr STRING, p_name STRING, p_size INT, s2 INT, r INT, dr INT, cud DOUBLE, fv1 INT) POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@part_5 PREHOOK: query: explain from noop(on part partition by p_mfgr order by p_name) INSERT OVERWRITE TABLE part_4 select p_mfgr, p_name, p_size, rank() over (distribute by p_mfgr sort by p_name) as r, dense_rank() over (distribute by p_mfgr sort by p_name) as dr, sum(p_retailprice) over (distribute by p_mfgr sort by p_name rows between unbounded preceding and current row) as s INSERT OVERWRITE TABLE part_5 select p_mfgr,p_name, p_size, round(sum(p_size) over (distribute by p_mfgr sort by p_size range between 5 preceding and current row),1) as s2, rank() over (distribute by p_mfgr sort by p_mfgr, p_name) as r, dense_rank() over (distribute by p_mfgr sort by p_mfgr, p_name) as dr, cume_dist() over (distribute by p_mfgr sort by p_mfgr, p_name) as cud, first_value(p_size, true) over w1 as fv1 window w1 as (distribute by p_mfgr sort by p_mfgr, p_name rows between 2 preceding and 2 following) PREHOOK: type: QUERY POSTHOOK: query: explain from noop(on part partition by p_mfgr order by p_name) INSERT OVERWRITE TABLE part_4 select p_mfgr, p_name, p_size, rank() over (distribute by p_mfgr sort by p_name) as r, dense_rank() over (distribute by p_mfgr sort by p_name) as dr, sum(p_retailprice) over (distribute by p_mfgr sort by p_name rows between unbounded preceding and current row) as s INSERT OVERWRITE TABLE part_5 select p_mfgr,p_name, p_size, round(sum(p_size) over (distribute by p_mfgr sort by p_size range between 5 preceding and current row),1) as s2, rank() over (distribute by p_mfgr sort by p_mfgr, p_name) as r, dense_rank() over (distribute by p_mfgr sort by p_mfgr, p_name) as dr, cume_dist() over (distribute by p_mfgr sort by p_mfgr, p_name) as cud, first_value(p_size, true) over w1 as fv1 window w1 as (distribute by p_mfgr sort by p_mfgr, p_name rows between 2 preceding and 2 following) POSTHOOK: type: QUERY Plan not optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Reducer 5 <- Reducer 4 (SIMPLE_EDGE) Reducer 4 <- Reducer 2 (SIMPLE_EDGE) Stage-5 Stats-Aggr Operator Stage-1 Move Operator table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.part_5","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Stage-3 Dependency Collection{} Stage-2 Reducer 3 File Output Operator [FS_9] compressed:true Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.part_4","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_7] outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE PTF Operator [PTF_6] Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"_col2","name:":"windowingtablefunction","order by:":"_col1"}] Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator [SEL_5] | outputColumnNames:["_col1","_col2","_col5","_col7"] | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_4] key expressions:_col2 (type: string), _col1 (type: string) Map-reduce partition columns:_col2 (type: string) sort order:++ Statistics:Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col5 (type: int), _col7 (type: double) PTF Operator [PTF_3] Function definitions:[{"Input definition":{"type:":"TABLE"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col1"}}] Statistics:Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_2] | outputColumnNames:["_col1","_col2","_col5","_col7"] | Statistics:Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_1] key expressions:p_mfgr (type: string), p_name (type: string) Map-reduce partition columns:p_mfgr (type: string) sort order:++ Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE value expressions:p_size (type: int), p_retailprice (type: double) TableScan [TS_0] alias:part Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE Reducer 5 File Output Operator [FS_20] compressed:true Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.part_5","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_17] outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE PTF Operator [PTF_16] Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"_col3","name:":"windowingtablefunction","order by:":"_col3, _col2"}] Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator [SEL_15] | outputColumnNames:["_col0","_col2","_col3","_col6"] | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE |<-Reducer 4 [SIMPLE_EDGE] Reduce Output Operator [RS_14] key expressions:_col2 (type: string), _col1 (type: string) Map-reduce partition columns:_col2 (type: string) sort order:++ Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE value expressions:sum_window_0 (type: bigint), _col5 (type: int) Select Operator [SEL_13] outputColumnNames:["_col1","_col2","_col5","sum_window_0"] Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE PTF Operator [PTF_12] Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"_col2","name:":"windowingtablefunction","order by:":"_col5"}] Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator [SEL_11] | outputColumnNames:["_col1","_col2","_col5"] | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_10] key expressions:_col2 (type: string), _col5 (type: int) Map-reduce partition columns:_col2 (type: string) sort order:++ Statistics:Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: string) Please refer to the previous PTF Operator [PTF_3] Stage-4 Stats-Aggr Operator Stage-0 Move Operator table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.part_4","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Please refer to the previous Stage-3 PREHOOK: query: explain select p_mfgr, p_name, rank() over (partition by p_mfgr,p_name) as r, dense_rank() over (partition by p_mfgr,p_name) as dr, p_size, sum(p_size) over (partition by p_mfgr,p_name rows between unbounded preceding and current row) as s1 from noop(on noopwithmap(on noop(on noop(on part partition by p_mfgr order by p_mfgr) ) partition by p_mfgr,p_name order by p_mfgr,p_name) partition by p_mfgr,p_name order by p_mfgr,p_name) PREHOOK: type: QUERY POSTHOOK: query: explain select p_mfgr, p_name, rank() over (partition by p_mfgr,p_name) as r, dense_rank() over (partition by p_mfgr,p_name) as dr, p_size, sum(p_size) over (partition by p_mfgr,p_name rows between unbounded preceding and current row) as s1 from noop(on noopwithmap(on noop(on noop(on part partition by p_mfgr order by p_mfgr) ) partition by p_mfgr,p_name order by p_mfgr,p_name) partition by p_mfgr,p_name order by p_mfgr,p_name) POSTHOOK: type: QUERY Plan not optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 4 File Output Operator [FS_13] compressed:true Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_11] outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE PTF Operator [PTF_10] Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"_col2, _col1","name:":"windowingtablefunction","order by:":"_col2, _col1"}] Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator [SEL_9] | outputColumnNames:["_col1","_col2","_col5"] | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE |<-Reducer 3 [SIMPLE_EDGE] Reduce Output Operator [RS_8] key expressions:_col2 (type: string), _col1 (type: string) Map-reduce partition columns:_col2 (type: string), _col1 (type: string) sort order:++ Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE value expressions:_col5 (type: int) PTF Operator [PTF_7] Function definitions:[{"Input definition":{"type:":"PTFCOMPONENT"}},{"Partition table definition":{"partition by:":"_col2, _col1","name:":"noopwithmap","order by:":"_col2, _col1"}},{"Partition table definition":{"partition by:":"_col2, _col1","name:":"noop","order by:":"_col2, _col1"}}] Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator [SEL_6] | outputColumnNames:["_col1","_col2","_col5"] | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_5] key expressions:_col2 (type: string), _col1 (type: string) Map-reduce partition columns:_col2 (type: string), _col1 (type: string) sort order:++ Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col5 (type: int) PTF Operator [PTF_4] Function definitions:[{"Input definition":{"type:":"PTFCOMPONENT"}},{"Partition table definition":{"partition by:":"_col2, _col1","name:":"noopwithmap","order by:":"_col2, _col1"}},{"Partition table definition":{"partition by:":"_col2, _col1","name:":"noop","order by:":"_col2, _col1"}}] Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator [PTF_3] Function definitions:[{"Input definition":{"type:":"TABLE"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col2"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col2"}}] Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_2] | outputColumnNames:["_col1","_col2","_col5"] | Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_1] key expressions:p_mfgr (type: string) Map-reduce partition columns:p_mfgr (type: string) sort order:+ Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE value expressions:p_name (type: string), p_size (type: int) TableScan [TS_0] alias:part Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select p_mfgr, p_name, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, p_size, sum(p_size) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 from noop(on noop(on noop(on noop(on part partition by p_mfgr order by p_mfgr) ) partition by p_mfgr,p_name order by p_mfgr,p_name) partition by p_mfgr order by p_mfgr ) PREHOOK: type: QUERY POSTHOOK: query: explain select p_mfgr, p_name, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, p_size, sum(p_size) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 from noop(on noop(on noop(on noop(on part partition by p_mfgr order by p_mfgr) ) partition by p_mfgr,p_name order by p_mfgr,p_name) partition by p_mfgr order by p_mfgr ) POSTHOOK: type: QUERY Plan not optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Reducer 5 <- Reducer 4 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 5 File Output Operator [FS_15] compressed:true Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_13] outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE PTF Operator [PTF_12] Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"_col2","name:":"windowingtablefunction","order by:":"_col1"}] Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator [SEL_11] | outputColumnNames:["_col1","_col2","_col5"] | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE |<-Reducer 4 [SIMPLE_EDGE] Reduce Output Operator [RS_10] key expressions:_col2 (type: string), _col1 (type: string) Map-reduce partition columns:_col2 (type: string) sort order:++ Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE value expressions:_col5 (type: int) PTF Operator [PTF_9] Function definitions:[{"Input definition":{"type:":"PTFCOMPONENT"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col2"}}] Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator [SEL_8] | outputColumnNames:["_col1","_col2","_col5"] | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE |<-Reducer 3 [SIMPLE_EDGE] Reduce Output Operator [RS_7] key expressions:_col2 (type: string) Map-reduce partition columns:_col2 (type: string) sort order:+ Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE value expressions:_col1 (type: string), _col5 (type: int) PTF Operator [PTF_6] Function definitions:[{"Input definition":{"type:":"PTFCOMPONENT"}},{"Partition table definition":{"partition by:":"_col2, _col1","name:":"noop","order by:":"_col2, _col1"}}] Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator [SEL_5] | outputColumnNames:["_col1","_col2","_col5"] | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_4] key expressions:_col2 (type: string), _col1 (type: string) Map-reduce partition columns:_col2 (type: string), _col1 (type: string) sort order:++ Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col5 (type: int) PTF Operator [PTF_3] Function definitions:[{"Input definition":{"type:":"TABLE"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col2"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col2"}}] Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_2] | outputColumnNames:["_col1","_col2","_col5"] | Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_1] key expressions:p_mfgr (type: string) Map-reduce partition columns:p_mfgr (type: string) sort order:+ Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE value expressions:p_name (type: string), p_size (type: int) TableScan [TS_0] alias:part Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select p_mfgr, p_name, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, p_size, sum(p_size) over (partition by p_mfgr order by p_name) as s1 from noop(on noop(on noop(on noop(on part partition by p_mfgr,p_name order by p_mfgr,p_name) ) partition by p_mfgr order by p_mfgr)) PREHOOK: type: QUERY POSTHOOK: query: explain select p_mfgr, p_name, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, p_size, sum(p_size) over (partition by p_mfgr order by p_name) as s1 from noop(on noop(on noop(on noop(on part partition by p_mfgr,p_name order by p_mfgr,p_name) ) partition by p_mfgr order by p_mfgr)) POSTHOOK: type: QUERY Plan not optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 4 File Output Operator [FS_12] compressed:true Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_10] outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE PTF Operator [PTF_9] Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"_col2","name:":"windowingtablefunction","order by:":"_col1"}] Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator [SEL_8] | outputColumnNames:["_col1","_col2","_col5"] | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE |<-Reducer 3 [SIMPLE_EDGE] Reduce Output Operator [RS_7] key expressions:_col2 (type: string), _col1 (type: string) Map-reduce partition columns:_col2 (type: string) sort order:++ Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE value expressions:_col5 (type: int) PTF Operator [PTF_6] Function definitions:[{"Input definition":{"type:":"PTFCOMPONENT"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col2"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col2"}}] Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator [SEL_5] | outputColumnNames:["_col1","_col2","_col5"] | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_4] key expressions:_col2 (type: string) Map-reduce partition columns:_col2 (type: string) sort order:+ Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: string), _col5 (type: int) PTF Operator [PTF_3] Function definitions:[{"Input definition":{"type:":"TABLE"}},{"Partition table definition":{"partition by:":"_col2, _col1","name:":"noop","order by:":"_col2, _col1"}},{"Partition table definition":{"partition by:":"_col2, _col1","name:":"noop","order by:":"_col2, _col1"}}] Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_2] | outputColumnNames:["_col1","_col2","_col5"] | Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_1] key expressions:p_mfgr (type: string), p_name (type: string) Map-reduce partition columns:p_mfgr (type: string), p_name (type: string) sort order:++ Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE value expressions:p_size (type: int) TableScan [TS_0] alias:part Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select distinct src.* from src PREHOOK: type: QUERY POSTHOOK: query: explain select distinct src.* from src POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 3 File Output Operator [FS_8] compressed:true Statistics:Num rows: 250 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Group By Operator [GBY_6] | keys:KEY._col0 (type: string), KEY._col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 250 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_5] key expressions:_col0 (type: string), _col1 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string) sort order:++ Statistics:Num rows: 500 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Group By Operator [GBY_4] | keys:KEY._col0 (type: string), KEY._col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 500 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_3] key expressions:_col0 (type: string), _col1 (type: string) Map-reduce partition columns:rand() (type: double) sort order:++ Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_1] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_0] alias:src Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select explode(array('a', 'b')) PREHOOK: type: QUERY POSTHOOK: query: explain select explode(array('a', 'b')) POSTHOOK: type: QUERY Plan not optimized by CBO due to missing feature [Others]. Stage-0 Fetch Operator limit:-1 UDTF Operator [UDTF_2] function name:explode Select Operator [SEL_1] outputColumnNames:["_col0"] TableScan [TS_0] alias:_dummy_table PREHOOK: query: CREATE TABLE T1(key STRING, val STRING) STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@T1 POSTHOOK: query: CREATE TABLE T1(key STRING, val STRING) STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@T1 PREHOOK: query: CREATE TABLE T2(key STRING, val STRING) STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@T2 POSTHOOK: query: CREATE TABLE T2(key STRING, val STRING) STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@T2 PREHOOK: query: CREATE TABLE T3(key STRING, val STRING) STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@T3 POSTHOOK: query: CREATE TABLE T3(key STRING, val STRING) STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@T3 PREHOOK: query: CREATE TABLE T4(key STRING, val STRING) STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@T4 POSTHOOK: query: CREATE TABLE T4(key STRING, val STRING) STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@T4 PREHOOK: query: CREATE TABLE dest_j1(key INT, value STRING) STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@dest_j1 POSTHOOK: query: CREATE TABLE dest_j1(key INT, value STRING) STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@dest_j1 PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1 PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@t1 POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1 POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@t1 PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2 PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@t2 POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2 POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@t2 PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T3.txt' INTO TABLE T3 PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@t3 POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T3.txt' INTO TABLE T3 POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@t3 PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T4 PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@t4 POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T4 POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@t4 PREHOOK: query: explain FROM src src1 JOIN src src2 ON (src1.key = src2.key) INSERT OVERWRITE TABLE dest_j1 select src1.key, src2.value PREHOOK: type: QUERY POSTHOOK: query: explain FROM src src1 JOIN src src2 ON (src1.key = src2.key) INSERT OVERWRITE TABLE dest_j1 select src1.key, src2.value POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) Stage-3 Stats-Aggr Operator Stage-0 Move Operator table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.dest_j1","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Stage-2 Dependency Collection{} Stage-1 Reducer 2 File Output Operator [FS_11] compressed:true Statistics:Num rows: 1219 Data size: 115805 Basic stats: COMPLETE Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.dest_j1","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_9] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 1219 Data size: 115805 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator [MERGEJOIN_16] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} | outputColumnNames:["_col1","_col2"] | Statistics:Num rows: 1219 Data size: 216982 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_5] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col1 (type: string) | Select Operator [SEL_1] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_14] | predicate:key is not null (type: boolean) | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:src1 | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 3 [SIMPLE_EDGE] Reduce Output Operator [RS_7] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_3] outputColumnNames:["_col0"] Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator [FIL_15] predicate:key is not null (type: boolean) Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_2] alias:src1 Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: FROM src src1 JOIN src src2 ON (src1.key = src2.key) INSERT OVERWRITE TABLE dest_j1 select src1.key, src2.value PREHOOK: type: QUERY PREHOOK: Input: default@src PREHOOK: Output: default@dest_j1 POSTHOOK: query: FROM src src1 JOIN src src2 ON (src1.key = src2.key) INSERT OVERWRITE TABLE dest_j1 select src1.key, src2.value POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@dest_j1 POSTHOOK: Lineage: dest_j1.key EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: dest_j1.value SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: explain select /*+ STREAMTABLE(a) */ * FROM T1 a JOIN T2 b ON a.key = b.key JOIN T3 c ON b.key = c.key JOIN T4 d ON c.key = d.key PREHOOK: type: QUERY POSTHOOK: query: explain select /*+ STREAMTABLE(a) */ * FROM T1 a JOIN T2 b ON a.key = b.key JOIN T3 c ON b.key = c.key JOIN T4 d ON c.key = d.key POSTHOOK: type: QUERY Plan not optimized by CBO due to missing feature [Hint]. Vertex dependency in root stage Map 1 <- Map 2 (BROADCAST_EDGE), Map 3 (BROADCAST_EDGE), Map 4 (BROADCAST_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Map 1 File Output Operator [FS_14] compressed:true Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_13] outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Map Join Operator [MAPJOIN_31] | condition map:[{"":"Inner Join 0 to 1"},{"":"Inner Join 1 to 2"},{"":"Inner Join 2 to 3"}] | keys:{"Map 1":"key (type: string)","Map 2":"key (type: string)","Map 3":"key (type: string)","Map 4":"key (type: string)"} | outputColumnNames:["_col0","_col1","_col5","_col6","_col10","_col11","_col15","_col16"] | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE |<-Map 4 [BROADCAST_EDGE] | Reduce Output Operator [RS_11] | key expressions:key (type: string) | Map-reduce partition columns:key (type: string) | sort order:+ | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE | value expressions:val (type: string) | Filter Operator [FIL_30] | predicate:key is not null (type: boolean) | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE | TableScan [TS_3] | alias:d | Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE |<-Map 3 [BROADCAST_EDGE] | Reduce Output Operator [RS_9] | key expressions:key (type: string) | Map-reduce partition columns:key (type: string) | sort order:+ | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE | value expressions:val (type: string) | Filter Operator [FIL_29] | predicate:key is not null (type: boolean) | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE | TableScan [TS_2] | alias:c | Statistics:Num rows: 0 Data size: 20 Basic stats: PARTIAL Column stats: NONE |<-Map 2 [BROADCAST_EDGE] | Reduce Output Operator [RS_7] | key expressions:key (type: string) | Map-reduce partition columns:key (type: string) | sort order:+ | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE | value expressions:val (type: string) | Filter Operator [FIL_28] | predicate:key is not null (type: boolean) | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE | TableScan [TS_1] | alias:b | Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE |<-Filter Operator [FIL_27] predicate:key is not null (type: boolean) Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE TableScan [TS_0] alias:a Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE PREHOOK: query: explain select /*+ STREAMTABLE(a,c) */ * FROM T1 a JOIN T2 b ON a.key = b.key JOIN T3 c ON b.key = c.key JOIN T4 d ON c.key = d.key PREHOOK: type: QUERY POSTHOOK: query: explain select /*+ STREAMTABLE(a,c) */ * FROM T1 a JOIN T2 b ON a.key = b.key JOIN T3 c ON b.key = c.key JOIN T4 d ON c.key = d.key POSTHOOK: type: QUERY Plan not optimized by CBO due to missing feature [Hint]. Vertex dependency in root stage Map 1 <- Map 2 (BROADCAST_EDGE), Map 3 (BROADCAST_EDGE), Map 4 (BROADCAST_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Map 1 File Output Operator [FS_14] compressed:true Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_13] outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Map Join Operator [MAPJOIN_31] | condition map:[{"":"Inner Join 0 to 1"},{"":"Inner Join 1 to 2"},{"":"Inner Join 2 to 3"}] | keys:{"Map 1":"key (type: string)","Map 2":"key (type: string)","Map 3":"key (type: string)","Map 4":"key (type: string)"} | outputColumnNames:["_col0","_col1","_col5","_col6","_col10","_col11","_col15","_col16"] | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE |<-Map 4 [BROADCAST_EDGE] | Reduce Output Operator [RS_11] | key expressions:key (type: string) | Map-reduce partition columns:key (type: string) | sort order:+ | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE | value expressions:val (type: string) | Filter Operator [FIL_30] | predicate:key is not null (type: boolean) | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE | TableScan [TS_3] | alias:d | Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE |<-Map 3 [BROADCAST_EDGE] | Reduce Output Operator [RS_9] | key expressions:key (type: string) | Map-reduce partition columns:key (type: string) | sort order:+ | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE | value expressions:val (type: string) | Filter Operator [FIL_29] | predicate:key is not null (type: boolean) | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE | TableScan [TS_2] | alias:c | Statistics:Num rows: 0 Data size: 20 Basic stats: PARTIAL Column stats: NONE |<-Map 2 [BROADCAST_EDGE] | Reduce Output Operator [RS_7] | key expressions:key (type: string) | Map-reduce partition columns:key (type: string) | sort order:+ | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE | value expressions:val (type: string) | Filter Operator [FIL_28] | predicate:key is not null (type: boolean) | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE | TableScan [TS_1] | alias:b | Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE |<-Filter Operator [FIL_27] predicate:key is not null (type: boolean) Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE TableScan [TS_0] alias:a Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE PREHOOK: query: explain FROM T1 a JOIN src c ON c.key+1=a.key select /*+ STREAMTABLE(a) */ sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key)) PREHOOK: type: QUERY POSTHOOK: query: explain FROM T1 a JOIN src c ON c.key+1=a.key select /*+ STREAMTABLE(a) */ sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key)) POSTHOOK: type: QUERY Plan not optimized by CBO due to missing feature [Hint]. Vertex dependency in root stage Reducer 3 <- Map 2 (SIMPLE_EDGE) Map 2 <- Map 1 (BROADCAST_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 4 File Output Operator [FS_13] compressed:true Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Group By Operator [GBY_11] | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE |<-Reducer 3 [SIMPLE_EDGE] Reduce Output Operator [RS_10] sort order: Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE value expressions:_col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint) Group By Operator [GBY_9] | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE |<-Map 2 [SIMPLE_EDGE] Reduce Output Operator [RS_8] Map-reduce partition columns:rand() (type: double) sort order: Statistics:Num rows: 275 Data size: 23925 Basic stats: COMPLETE Column stats: NONE value expressions:hash(_col0) (type: int), hash(_col1) (type: int), hash(_col5) (type: int) Map Join Operator [MAPJOIN_18] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"Map 1":"UDFToDouble(key) (type: double)","Map 2":"(key + 1) (type: double)"} | outputColumnNames:["_col0","_col1","_col5"] | Statistics:Num rows: 275 Data size: 23925 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [BROADCAST_EDGE] | Reduce Output Operator [RS_3] | key expressions:UDFToDouble(key) (type: double) | Map-reduce partition columns:UDFToDouble(key) (type: double) | sort order:+ | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE | value expressions:key (type: string), val (type: string) | Filter Operator [FIL_16] | predicate:UDFToDouble(key) is not null (type: boolean) | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE | TableScan [TS_0] | alias:a | Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE |<-Filter Operator [FIL_17] predicate:(key + 1) is not null (type: boolean) Statistics:Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_1] alias:c Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: FROM T1 a JOIN src c ON c.key+1=a.key select /*+ STREAMTABLE(a) */ sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key)) PREHOOK: type: QUERY PREHOOK: Input: default@src PREHOOK: Input: default@t1 #### A masked pattern was here #### POSTHOOK: query: FROM T1 a JOIN src c ON c.key+1=a.key select /*+ STREAMTABLE(a) */ sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key)) POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Input: default@t1 #### A masked pattern was here #### 198 6274 194 PREHOOK: query: explain select * FROM (select src.* FROM src) x JOIN (select src.* FROM src) Y ON (x.key = Y.key) PREHOOK: type: QUERY POSTHOOK: query: explain select * FROM (select src.* FROM src) x JOIN (select src.* FROM src) Y ON (x.key = Y.key) POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_10] compressed:true Statistics:Num rows: 1219 Data size: 433964 Basic stats: COMPLETE Column stats: COMPLETE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Merge Join Operator [MERGEJOIN_15] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 1219 Data size: 433964 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_5] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col1 (type: string) | Select Operator [SEL_1] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_13] | predicate:key is not null (type: boolean) | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:src | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 3 [SIMPLE_EDGE] Reduce Output Operator [RS_7] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: string) Select Operator [SEL_3] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator [FIL_14] predicate:key is not null (type: boolean) Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_2] alias:src Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select /*+ mapjoin(k)*/ sum(hash(k.key)), sum(hash(v.val)) from T1 k join T1 v on k.key=v.val PREHOOK: type: QUERY POSTHOOK: query: explain select /*+ mapjoin(k)*/ sum(hash(k.key)), sum(hash(v.val)) from T1 k join T1 v on k.key=v.val POSTHOOK: type: QUERY Plan not optimized by CBO due to missing feature [Hint]. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Map 1 <- Map 4 (BROADCAST_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 3 File Output Operator [FS_13] compressed:true Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Group By Operator [GBY_11] | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_10] sort order: Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE value expressions:_col0 (type: bigint), _col1 (type: bigint) Group By Operator [GBY_9] | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_8] Map-reduce partition columns:rand() (type: double) sort order: Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE value expressions:hash(_col0) (type: int), hash(_col6) (type: int) Map Join Operator [MAPJOIN_18] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"Map 1":"key (type: string)","Map 4":"val (type: string)"} | outputColumnNames:["_col0","_col6"] | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE |<-Map 4 [BROADCAST_EDGE] | Reduce Output Operator [RS_5] | key expressions:val (type: string) | Map-reduce partition columns:val (type: string) | sort order:+ | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE | Filter Operator [FIL_17] | predicate:val is not null (type: boolean) | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE | TableScan [TS_1] | alias:v | Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE |<-Filter Operator [FIL_16] predicate:key is not null (type: boolean) Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE TableScan [TS_0] alias:k Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE PREHOOK: query: explain select sum(hash(k.key)), sum(hash(v.val)) from T1 k join T1 v on k.key=v.key PREHOOK: type: QUERY POSTHOOK: query: explain select sum(hash(k.key)), sum(hash(v.val)) from T1 k join T1 v on k.key=v.key POSTHOOK: type: QUERY Plan not optimized by CBO due to missing statistics. Please check log for more details. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Map 1 <- Map 4 (BROADCAST_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 3 File Output Operator [FS_13] compressed:true Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Group By Operator [GBY_11] | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_10] sort order: Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE value expressions:_col0 (type: bigint), _col1 (type: bigint) Group By Operator [GBY_9] | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_8] Map-reduce partition columns:rand() (type: double) sort order: Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE value expressions:hash(_col0) (type: int), hash(_col6) (type: int) Map Join Operator [MAPJOIN_18] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"Map 1":"key (type: string)","Map 4":"key (type: string)"} | outputColumnNames:["_col0","_col6"] | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE |<-Map 4 [BROADCAST_EDGE] | Reduce Output Operator [RS_5] | key expressions:key (type: string) | Map-reduce partition columns:key (type: string) | sort order:+ | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE | value expressions:val (type: string) | Filter Operator [FIL_17] | predicate:key is not null (type: boolean) | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE | TableScan [TS_1] | alias:v | Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE |<-Filter Operator [FIL_16] predicate:key is not null (type: boolean) Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE TableScan [TS_0] alias:k Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE PREHOOK: query: explain select count(1) from T1 a join T1 b on a.key = b.key PREHOOK: type: QUERY POSTHOOK: query: explain select count(1) from T1 a join T1 b on a.key = b.key POSTHOOK: type: QUERY Plan not optimized by CBO due to missing statistics. Please check log for more details. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Map 1 <- Map 4 (BROADCAST_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 3 File Output Operator [FS_13] compressed:true Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Group By Operator [GBY_11] | aggregations:["count(VALUE._col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_10] sort order: Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions:_col0 (type: bigint) Group By Operator [GBY_9] | aggregations:["count(1)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_8] Map-reduce partition columns:rand() (type: double) sort order: Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Map Join Operator [MAPJOIN_18] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"Map 1":"key (type: string)","Map 4":"key (type: string)"} | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE |<-Map 4 [BROADCAST_EDGE] | Reduce Output Operator [RS_5] | key expressions:key (type: string) | Map-reduce partition columns:key (type: string) | sort order:+ | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE | Filter Operator [FIL_17] | predicate:key is not null (type: boolean) | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE | TableScan [TS_1] | alias:b | Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE |<-Filter Operator [FIL_16] predicate:key is not null (type: boolean) Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE TableScan [TS_0] alias:a Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE PREHOOK: query: explain FROM T1 a LEFT OUTER JOIN T2 c ON c.key+1=a.key select sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key)) PREHOOK: type: QUERY POSTHOOK: query: explain FROM T1 a LEFT OUTER JOIN T2 c ON c.key+1=a.key select sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key)) POSTHOOK: type: QUERY Plan not optimized by CBO due to missing statistics. Please check log for more details. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Map 1 <- Map 4 (BROADCAST_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 3 File Output Operator [FS_11] compressed:true Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Group By Operator [GBY_9] | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_8] sort order: Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE value expressions:_col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint) Group By Operator [GBY_7] | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_6] Map-reduce partition columns:rand() (type: double) sort order: Statistics:Num rows: 0 Data size: 33 Basic stats: PARTIAL Column stats: NONE value expressions:hash(_col0) (type: int), hash(_col1) (type: int), hash(_col5) (type: int) Map Join Operator [MAPJOIN_14] | condition map:[{"":"Left Outer Join0 to 1"}] | keys:{"Map 1":"UDFToDouble(key) (type: double)","Map 4":"(key + 1) (type: double)"} | outputColumnNames:["_col0","_col1","_col5"] | Statistics:Num rows: 0 Data size: 33 Basic stats: PARTIAL Column stats: NONE |<-Map 4 [BROADCAST_EDGE] | Reduce Output Operator [RS_3] | key expressions:(key + 1) (type: double) | Map-reduce partition columns:(key + 1) (type: double) | sort order:+ | Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE | value expressions:key (type: string) | TableScan [TS_1] | alias:c | Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE |<-TableScan [TS_0] alias:a Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE PREHOOK: query: explain FROM T1 a RIGHT OUTER JOIN T2 c ON c.key+1=a.key select /*+ STREAMTABLE(a) */ sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key)) PREHOOK: type: QUERY POSTHOOK: query: explain FROM T1 a RIGHT OUTER JOIN T2 c ON c.key+1=a.key select /*+ STREAMTABLE(a) */ sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key)) POSTHOOK: type: QUERY Plan not optimized by CBO due to missing feature [Hint]. Vertex dependency in root stage Reducer 3 <- Map 2 (SIMPLE_EDGE) Map 2 <- Map 1 (BROADCAST_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 4 File Output Operator [FS_11] compressed:true Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Group By Operator [GBY_9] | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE |<-Reducer 3 [SIMPLE_EDGE] Reduce Output Operator [RS_8] sort order: Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE value expressions:_col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint) Group By Operator [GBY_7] | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE |<-Map 2 [SIMPLE_EDGE] Reduce Output Operator [RS_6] Map-reduce partition columns:rand() (type: double) sort order: Statistics:Num rows: 0 Data size: 33 Basic stats: PARTIAL Column stats: NONE value expressions:hash(_col0) (type: int), hash(_col1) (type: int), hash(_col5) (type: int) Map Join Operator [MAPJOIN_14] | condition map:[{"":"Right Outer Join0 to 1"}] | keys:{"Map 1":"UDFToDouble(key) (type: double)","Map 2":"(key + 1) (type: double)"} | outputColumnNames:["_col0","_col1","_col5"] | Statistics:Num rows: 0 Data size: 33 Basic stats: PARTIAL Column stats: NONE |<-Map 1 [BROADCAST_EDGE] | Reduce Output Operator [RS_2] | key expressions:UDFToDouble(key) (type: double) | Map-reduce partition columns:UDFToDouble(key) (type: double) | sort order:+ | Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE | value expressions:key (type: string), val (type: string) | TableScan [TS_0] | alias:a | Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE |<-TableScan [TS_1] alias:c Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE PREHOOK: query: explain FROM T1 a FULL OUTER JOIN T2 c ON c.key+1=a.key select /*+ STREAMTABLE(a) */ sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key)) PREHOOK: type: QUERY POSTHOOK: query: explain FROM T1 a FULL OUTER JOIN T2 c ON c.key+1=a.key select /*+ STREAMTABLE(a) */ sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key)) POSTHOOK: type: QUERY Plan not optimized by CBO due to missing feature [Hint]. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 4 File Output Operator [FS_11] compressed:true Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Group By Operator [GBY_9] | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE |<-Reducer 3 [SIMPLE_EDGE] Reduce Output Operator [RS_8] sort order: Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE value expressions:_col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint) Group By Operator [GBY_7] | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_6] Map-reduce partition columns:rand() (type: double) sort order: Statistics:Num rows: 0 Data size: 33 Basic stats: PARTIAL Column stats: NONE value expressions:hash(_col0) (type: int), hash(_col1) (type: int), hash(_col5) (type: int) Merge Join Operator [MERGEJOIN_12] | condition map:[{"":"Outer Join 0 to 1"}] | keys:{"1":"(key + 1) (type: double)","0":"UDFToDouble(key) (type: double)"} | outputColumnNames:["_col0","_col1","_col5"] | Statistics:Num rows: 0 Data size: 33 Basic stats: PARTIAL Column stats: NONE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_2] | key expressions:UDFToDouble(key) (type: double) | Map-reduce partition columns:UDFToDouble(key) (type: double) | sort order:+ | Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE | value expressions:key (type: string), val (type: string) | TableScan [TS_0] | alias:a | Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE |<-Map 5 [SIMPLE_EDGE] Reduce Output Operator [RS_3] key expressions:(key + 1) (type: double) Map-reduce partition columns:(key + 1) (type: double) sort order:+ Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE value expressions:key (type: string) TableScan [TS_1] alias:c Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE PREHOOK: query: explain select /*+ mapjoin(v)*/ sum(hash(k.key)), sum(hash(v.val)) from T1 k left outer join T1 v on k.key+1=v.key PREHOOK: type: QUERY POSTHOOK: query: explain select /*+ mapjoin(v)*/ sum(hash(k.key)), sum(hash(v.val)) from T1 k left outer join T1 v on k.key+1=v.key POSTHOOK: type: QUERY Plan not optimized by CBO due to missing feature [Hint]. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Map 1 <- Map 4 (BROADCAST_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 3 File Output Operator [FS_11] compressed:true Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Group By Operator [GBY_9] | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE |<-Reducer 2 [SIMPLE_EDGE] Reduce Output Operator [RS_8] sort order: Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE value expressions:_col0 (type: bigint), _col1 (type: bigint) Group By Operator [GBY_7] | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] Reduce Output Operator [RS_6] Map-reduce partition columns:rand() (type: double) sort order: Statistics:Num rows: 0 Data size: 33 Basic stats: PARTIAL Column stats: NONE value expressions:hash(_col0) (type: int), hash(_col6) (type: int) Map Join Operator [MAPJOIN_14] | condition map:[{"":"Left Outer Join0 to 1"}] | keys:{"Map 1":"(key + 1) (type: double)","Map 4":"UDFToDouble(key) (type: double)"} | outputColumnNames:["_col0","_col6"] | Statistics:Num rows: 0 Data size: 33 Basic stats: PARTIAL Column stats: NONE |<-Map 4 [BROADCAST_EDGE] | Reduce Output Operator [RS_3] | key expressions:UDFToDouble(key) (type: double) | Map-reduce partition columns:UDFToDouble(key) (type: double) | sort order:+ | Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE | value expressions:val (type: string) | TableScan [TS_1] | alias:v | Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE |<-TableScan [TS_0] alias:k Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE