PREHOOK: query: CREATE TABLE dest_j1(key STRING, value STRING, val2 STRING) STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@dest_j1 POSTHOOK: query: CREATE TABLE dest_j1(key STRING, value STRING, val2 STRING) STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@dest_j1 PREHOOK: query: CREATE TABLE ss(k1 STRING,v1 STRING,k2 STRING,v2 STRING,k3 STRING,v3 STRING) STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@ss POSTHOOK: query: CREATE TABLE ss(k1 STRING,v1 STRING,k2 STRING,v2 STRING,k3 STRING,v3 STRING) STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@ss PREHOOK: query: CREATE TABLE sr(k1 STRING,v1 STRING,k2 STRING,v2 STRING,k3 STRING,v3 STRING) STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@sr POSTHOOK: query: CREATE TABLE sr(k1 STRING,v1 STRING,k2 STRING,v2 STRING,k3 STRING,v3 STRING) STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@sr PREHOOK: query: CREATE TABLE cs(k1 STRING,v1 STRING,k2 STRING,v2 STRING,k3 STRING,v3 STRING) STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@cs POSTHOOK: query: CREATE TABLE cs(k1 STRING,v1 STRING,k2 STRING,v2 STRING,k3 STRING,v3 STRING) STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@cs PREHOOK: query: INSERT OVERWRITE TABLE ss SELECT x.key,x.value,y.key,y.value,z.key,z.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN srcpart z ON (x.value = z.value and z.ds='2008-04-08' and z.hr=11) PREHOOK: type: QUERY PREHOOK: Input: default@src PREHOOK: Input: default@src1 PREHOOK: Input: default@srcpart PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 PREHOOK: Output: default@ss POSTHOOK: query: INSERT OVERWRITE TABLE ss SELECT x.key,x.value,y.key,y.value,z.key,z.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN srcpart z ON (x.value = z.value and z.ds='2008-04-08' and z.hr=11) POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Input: default@src1 POSTHOOK: Input: default@srcpart POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Output: default@ss POSTHOOK: Lineage: ss.k1 SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: ss.k2 EXPRESSION [(src)y.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: ss.k3 SIMPLE [(srcpart)z.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: ss.v1 SIMPLE [(src1)x.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: ss.v2 EXPRESSION [(src)y.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: ss.v3 SIMPLE [(srcpart)z.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: INSERT OVERWRITE TABLE sr SELECT x.key,x.value,y.key,y.value,z.key,z.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN srcpart z ON (x.value = z.value and z.ds='2008-04-08' and z.hr=12) PREHOOK: type: QUERY PREHOOK: Input: default@src PREHOOK: Input: default@src1 PREHOOK: Input: default@srcpart PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 PREHOOK: Output: default@sr POSTHOOK: query: INSERT OVERWRITE TABLE sr SELECT x.key,x.value,y.key,y.value,z.key,z.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN srcpart z ON (x.value = z.value and z.ds='2008-04-08' and z.hr=12) POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Input: default@src1 POSTHOOK: Input: default@srcpart POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 POSTHOOK: Output: default@sr POSTHOOK: Lineage: sr.k1 SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: sr.k2 EXPRESSION [(src)y.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: sr.k3 SIMPLE [(srcpart)z.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: sr.v1 SIMPLE [(src1)x.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: sr.v2 EXPRESSION [(src)y.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: sr.v3 SIMPLE [(srcpart)z.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: INSERT OVERWRITE TABLE cs SELECT x.key,x.value,y.key,y.value,z.key,z.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN srcpart z ON (x.value = z.value and z.ds='2008-04-08') PREHOOK: type: QUERY PREHOOK: Input: default@src PREHOOK: Input: default@src1 PREHOOK: Input: default@srcpart PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 PREHOOK: Output: default@cs POSTHOOK: query: INSERT OVERWRITE TABLE cs SELECT x.key,x.value,y.key,y.value,z.key,z.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN srcpart z ON (x.value = z.value and z.ds='2008-04-08') POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Input: default@src1 POSTHOOK: Input: default@srcpart POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 POSTHOOK: Output: default@cs POSTHOOK: Lineage: cs.k1 SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: cs.k2 EXPRESSION [(src)y.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: cs.k3 SIMPLE [(srcpart)z.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: cs.v1 SIMPLE [(src1)x.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: cs.v2 EXPRESSION [(src)y.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: cs.v3 SIMPLE [(srcpart)z.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: ANALYZE TABLE ss COMPUTE STATISTICS PREHOOK: type: QUERY PREHOOK: Input: default@ss PREHOOK: Output: default@ss POSTHOOK: query: ANALYZE TABLE ss COMPUTE STATISTICS POSTHOOK: type: QUERY POSTHOOK: Input: default@ss POSTHOOK: Output: default@ss PREHOOK: query: ANALYZE TABLE ss COMPUTE STATISTICS FOR COLUMNS k1,v1,k2,v2,k3,v3 PREHOOK: type: QUERY PREHOOK: Input: default@ss #### A masked pattern was here #### POSTHOOK: query: ANALYZE TABLE ss COMPUTE STATISTICS FOR COLUMNS k1,v1,k2,v2,k3,v3 POSTHOOK: type: QUERY POSTHOOK: Input: default@ss #### A masked pattern was here #### PREHOOK: query: ANALYZE TABLE sr COMPUTE STATISTICS PREHOOK: type: QUERY PREHOOK: Input: default@sr PREHOOK: Output: default@sr POSTHOOK: query: ANALYZE TABLE sr COMPUTE STATISTICS POSTHOOK: type: QUERY POSTHOOK: Input: default@sr POSTHOOK: Output: default@sr PREHOOK: query: ANALYZE TABLE sr COMPUTE STATISTICS FOR COLUMNS k1,v1,k2,v2,k3,v3 PREHOOK: type: QUERY PREHOOK: Input: default@sr #### A masked pattern was here #### POSTHOOK: query: ANALYZE TABLE sr COMPUTE STATISTICS FOR COLUMNS k1,v1,k2,v2,k3,v3 POSTHOOK: type: QUERY POSTHOOK: Input: default@sr #### A masked pattern was here #### PREHOOK: query: ANALYZE TABLE cs COMPUTE STATISTICS PREHOOK: type: QUERY PREHOOK: Input: default@cs PREHOOK: Output: default@cs POSTHOOK: query: ANALYZE TABLE cs COMPUTE STATISTICS POSTHOOK: type: QUERY POSTHOOK: Input: default@cs POSTHOOK: Output: default@cs PREHOOK: query: ANALYZE TABLE cs COMPUTE STATISTICS FOR COLUMNS k1,v1,k2,v2,k3,v3 PREHOOK: type: QUERY PREHOOK: Input: default@cs #### A masked pattern was here #### POSTHOOK: query: ANALYZE TABLE cs COMPUTE STATISTICS FOR COLUMNS k1,v1,k2,v2,k3,v3 POSTHOOK: type: QUERY POSTHOOK: Input: default@cs #### A masked pattern was here #### PREHOOK: query: EXPLAIN SELECT x.key, z.value, y.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN srcpart z ON (x.value = z.value and z.ds='2008-04-08' and z.hr=11) PREHOOK: type: QUERY POSTHOOK: query: EXPLAIN SELECT x.key, z.value, y.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN srcpart z ON (x.value = z.value and z.ds='2008-04-08' and z.hr=11) 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), Map 5 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_19] compressed:false Statistics:Num rows: 302 Data size: 3213 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_18] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE Merge Join Operator [MERGEJOIN_29] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"1":"_col3 (type: string)","0":"_col0 (type: string)"} | outputColumnNames:["_col0","_col4","_col5"] | Statistics:Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_14] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | Select Operator [SEL_2] | outputColumnNames:["_col0"] | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | Filter Operator [FIL_25] | predicate:value is not null (type: boolean) | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_0] | alias:z | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE |<-Reducer 4 [SIMPLE_EDGE] Reduce Output Operator [RS_16] key expressions:_col3 (type: string) Map-reduce partition columns:_col3 (type: string) sort order:+ Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE value expressions:_col1 (type: string), _col2 (type: string) Merge Join Operator [MERGEJOIN_28] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} | outputColumnNames:["_col1","_col2","_col3"] | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE |<-Map 3 [SIMPLE_EDGE] | Reduce Output Operator [RS_8] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | value expressions:_col1 (type: string) | Select Operator [SEL_4] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | Filter Operator [FIL_26] | predicate:key is not null (type: boolean) | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_3] | alias:y | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE |<-Map 5 [SIMPLE_EDGE] Reduce Output Operator [RS_10] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE value expressions:_col1 (type: string) Select Operator [SEL_6] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE Filter Operator [FIL_27] predicate:(key is not null and value is not null) (type: boolean) Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE TableScan [TS_5] alias:x Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: EXPLAIN select ss.k1,sr.k2,cs.k3,count(ss.v1),count(sr.v2),count(cs.v3) FROM ss,sr,cs,src d1,src d2,src d3,src1,srcpart where ss.k1 = d1.key and sr.k1 = d2.key and cs.k1 = d3.key and ss.k2 = sr.k2 and ss.k3 = sr.k3 and ss.v1 = src1.value and ss.v2 = srcpart.value and sr.v2 = cs.v2 and sr.v3 = cs.v3 and ss.v3='ssv3' and sr.v1='srv1' and src1.key = 'src1key' and srcpart.key = 'srcpartkey' and d1.value = 'd1value' and d2.value in ('2000Q1','2000Q2','2000Q3') and d3.value in ('2000Q1','2000Q2','2000Q3') group by ss.k1,sr.k2,cs.k3 order by ss.k1,sr.k2,cs.k3 limit 100 PREHOOK: type: QUERY POSTHOOK: query: EXPLAIN select ss.k1,sr.k2,cs.k3,count(ss.v1),count(sr.v2),count(cs.v3) FROM ss,sr,cs,src d1,src d2,src d3,src1,srcpart where ss.k1 = d1.key and sr.k1 = d2.key and cs.k1 = d3.key and ss.k2 = sr.k2 and ss.k3 = sr.k3 and ss.v1 = src1.value and ss.v2 = srcpart.value and sr.v2 = cs.v2 and sr.v3 = cs.v3 and ss.v3='ssv3' and sr.v1='srv1' and src1.key = 'src1key' and srcpart.key = 'srcpartkey' and d1.value = 'd1value' and d2.value in ('2000Q1','2000Q2','2000Q3') and d3.value in ('2000Q1','2000Q2','2000Q3') group by ss.k1,sr.k2,cs.k3 order by ss.k1,sr.k2,cs.k3 limit 100 POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) Reducer 14 <- Map 13 (SIMPLE_EDGE), Reducer 16 (SIMPLE_EDGE) Reducer 12 <- Map 11 (SIMPLE_EDGE), Reducer 14 (SIMPLE_EDGE) Reducer 5 <- Reducer 4 (SIMPLE_EDGE) Reducer 4 <- Reducer 12 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) Reducer 6 <- Reducer 5 (SIMPLE_EDGE) Reducer 9 <- Map 10 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) Reducer 16 <- Map 15 (SIMPLE_EDGE), Map 17 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 Reducer 6 File Output Operator [FS_71] compressed:false Statistics:Num rows: 100 Data size: 1000 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_70] Number of rows:100 Statistics:Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE Select Operator [SEL_69] | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] | Statistics:Num rows: 365 Data size: 3882 Basic stats: COMPLETE Column stats: NONE |<-Reducer 5 [SIMPLE_EDGE] Reduce Output Operator [RS_68] key expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string) sort order:+++ Statistics:Num rows: 365 Data size: 3882 Basic stats: COMPLETE Column stats: NONE value expressions:_col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint) Group By Operator [GBY_66] | aggregations:["count(VALUE._col0)","count(VALUE._col1)","count(VALUE._col2)"] | keys:KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] | Statistics:Num rows: 365 Data size: 3882 Basic stats: COMPLETE Column stats: NONE |<-Reducer 4 [SIMPLE_EDGE] Reduce Output Operator [RS_65] key expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string), _col2 (type: string) sort order:+++ Statistics:Num rows: 731 Data size: 7775 Basic stats: COMPLETE Column stats: NONE value expressions:_col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint) Group By Operator [GBY_64] aggregations:["count(_col3)","count(_col4)","count(_col5)"] keys:_col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] Statistics:Num rows: 731 Data size: 7775 Basic stats: COMPLETE Column stats: NONE Select Operator [SEL_62] outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] Statistics:Num rows: 731 Data size: 7775 Basic stats: COMPLETE Column stats: NONE Merge Join Operator [MERGEJOIN_111] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"1":"_col8 (type: string), _col10 (type: string)","0":"_col8 (type: string), _col10 (type: string)"} | outputColumnNames:["_col2","_col3","_col8","_col9","_col20","_col21"] | Statistics:Num rows: 731 Data size: 7775 Basic stats: COMPLETE Column stats: NONE |<-Reducer 12 [SIMPLE_EDGE] | Reduce Output Operator [RS_60] | key expressions:_col8 (type: string), _col10 (type: string) | Map-reduce partition columns:_col8 (type: string), _col10 (type: string) | sort order:++ | Statistics:Num rows: 665 Data size: 7069 Basic stats: COMPLETE Column stats: NONE | value expressions:_col6 (type: string), _col7 (type: string) | Select Operator [SEL_46] | outputColumnNames:["_col10","_col6","_col7","_col8"] | Statistics:Num rows: 665 Data size: 7069 Basic stats: COMPLETE Column stats: NONE | Merge Join Operator [MERGEJOIN_109] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"1":"_col5 (type: string)","0":"_col1 (type: string)"} | | outputColumnNames:["_col6","_col7","_col8","_col10"] | | Statistics:Num rows: 665 Data size: 7069 Basic stats: COMPLETE Column stats: NONE | |<-Map 11 [SIMPLE_EDGE] | | Reduce Output Operator [RS_42] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ | | Statistics:Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE | | Select Operator [SEL_19] | | outputColumnNames:["_col1"] | | Statistics:Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE | | Filter Operator [FIL_101] | | predicate:((key = 'src1key') and value is not null) (type: boolean) | | Statistics:Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE | | TableScan [TS_17] | | alias:src1 | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | |<-Reducer 14 [SIMPLE_EDGE] | Reduce Output Operator [RS_44] | key expressions:_col5 (type: string) | Map-reduce partition columns:_col5 (type: string) | sort order:+ | Statistics:Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE | value expressions:_col4 (type: string), _col6 (type: string), _col8 (type: string) | Merge Join Operator [MERGEJOIN_108] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"1":"_col2 (type: string)","0":"_col0 (type: string)"} | | outputColumnNames:["_col4","_col5","_col6","_col8"] | | Statistics:Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE | |<-Map 13 [SIMPLE_EDGE] | | Reduce Output Operator [RS_36] | | key expressions:_col0 (type: string) | | Map-reduce partition columns:_col0 (type: string) | | sort order:+ | | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE | | Select Operator [SEL_22] | | outputColumnNames:["_col0"] | | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE | | Filter Operator [FIL_102] | | predicate:((value = 'd1value') and key is not null) (type: boolean) | | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE | | TableScan [TS_20] | | alias:d1 | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | |<-Reducer 16 [SIMPLE_EDGE] | Reduce Output Operator [RS_38] | key expressions:_col2 (type: string) | Map-reduce partition columns:_col2 (type: string) | sort order:+ | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE | value expressions:_col3 (type: string), _col4 (type: string), _col6 (type: string) | Merge Join Operator [MERGEJOIN_107] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"1":"_col3 (type: string)","0":"_col1 (type: string)"} | | outputColumnNames:["_col2","_col3","_col4","_col6"] | | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE | |<-Map 15 [SIMPLE_EDGE] | | Reduce Output Operator [RS_30] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | | Select Operator [SEL_25] | | outputColumnNames:["_col1"] | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | | Filter Operator [FIL_103] | | predicate:((key = 'srcpartkey') and value is not null) (type: boolean) | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | | TableScan [TS_23] | | alias:srcpart | | Statistics:Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE | |<-Map 17 [SIMPLE_EDGE] | Reduce Output Operator [RS_32] | key expressions:_col3 (type: string) | Map-reduce partition columns:_col3 (type: string) | sort order:+ | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE | value expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string), _col4 (type: string) | Select Operator [SEL_28] | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE | Filter Operator [FIL_104] | predicate:((((((v3 = 'ssv3') and v2 is not null) and k1 is not null) and v1 is not null) and k2 is not null) and k3 is not null) (type: boolean) | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_26] | alias:ss | Statistics:Num rows: 85 Data size: 2945 Basic stats: COMPLETE Column stats: NONE |<-Reducer 3 [SIMPLE_EDGE] Reduce Output Operator [RS_58] key expressions:_col8 (type: string), _col10 (type: string) Map-reduce partition columns:_col8 (type: string), _col10 (type: string) sort order:++ Statistics:Num rows: 150 Data size: 1606 Basic stats: COMPLETE Column stats: NONE value expressions:_col2 (type: string), _col3 (type: string), _col9 (type: string) Merge Join Operator [MERGEJOIN_110] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"1":"_col3 (type: string), _col5 (type: string)","0":"_col1 (type: string), _col3 (type: string)"} | outputColumnNames:["_col2","_col3","_col8","_col9","_col10"] | Statistics:Num rows: 150 Data size: 1606 Basic stats: COMPLETE Column stats: NONE |<-Reducer 2 [SIMPLE_EDGE] | Reduce Output Operator [RS_53] | key expressions:_col1 (type: string), _col3 (type: string) | Map-reduce partition columns:_col1 (type: string), _col3 (type: string) | sort order:++ | Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE | value expressions:_col2 (type: string) | Merge Join Operator [MERGEJOIN_105] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} | | outputColumnNames:["_col1","_col2","_col3"] | | Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE | |<-Map 1 [SIMPLE_EDGE] | | Reduce Output Operator [RS_48] | | key expressions:_col0 (type: string) | | Map-reduce partition columns:_col0 (type: string) | | sort order:+ | | Statistics:Num rows: 22 Data size: 762 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col1 (type: string), _col2 (type: string), _col3 (type: string) | | Select Operator [SEL_1] | | outputColumnNames:["_col0","_col1","_col2","_col3"] | | Statistics:Num rows: 22 Data size: 762 Basic stats: COMPLETE Column stats: NONE | | Filter Operator [FIL_97] | | predicate:((k1 is not null and v2 is not null) and v3 is not null) (type: boolean) | | Statistics:Num rows: 22 Data size: 762 Basic stats: COMPLETE Column stats: NONE | | TableScan [TS_0] | | alias:cs | | Statistics:Num rows: 170 Data size: 5890 Basic stats: COMPLETE Column stats: NONE | |<-Map 7 [SIMPLE_EDGE] | Reduce Output Operator [RS_50] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE | Select Operator [SEL_4] | outputColumnNames:["_col0"] | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE | Filter Operator [FIL_98] | predicate:((value) IN ('2000Q1', '2000Q2', '2000Q3') and key is not null) (type: boolean) | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_2] | alias:d1 | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE |<-Reducer 9 [SIMPLE_EDGE] Reduce Output Operator [RS_55] key expressions:_col3 (type: string), _col5 (type: string) Map-reduce partition columns:_col3 (type: string), _col5 (type: string) sort order:++ Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE value expressions:_col2 (type: string), _col4 (type: string) Merge Join Operator [MERGEJOIN_106] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} | outputColumnNames:["_col2","_col3","_col4","_col5"] | Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE |<-Map 10 [SIMPLE_EDGE] | Reduce Output Operator [RS_14] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE | Select Operator [SEL_10] | outputColumnNames:["_col0"] | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE | Filter Operator [FIL_100] | predicate:((value) IN ('2000Q1', '2000Q2', '2000Q3') and key is not null) (type: boolean) | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_8] | alias:d1 | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE |<-Map 8 [SIMPLE_EDGE] Reduce Output Operator [RS_12] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE value expressions:_col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) Select Operator [SEL_7] outputColumnNames:["_col0","_col2","_col3","_col4","_col5"] Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE Filter Operator [FIL_99] predicate:((((((v1 = 'srv1') and k1 is not null) and v2 is not null) and v3 is not null) and k2 is not null) and k3 is not null) (type: boolean) Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE TableScan [TS_5] alias:sr Statistics:Num rows: 85 Data size: 2945 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: explain SELECT x.key, z.value, y.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN (select * from src1 union select * from src)z ON (x.value = z.value) union SELECT x.key, z.value, y.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN (select * from src1 union select * from src)z ON (x.value = z.value) PREHOOK: type: QUERY POSTHOOK: query: explain SELECT x.key, z.value, y.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN (select * from src1 union select * from src)z ON (x.value = z.value) union SELECT x.key, z.value, y.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN (select * from src1 union select * from src)z ON (x.value = z.value) POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE), Union 3 (CONTAINS) Reducer 12 <- Map 11 (SIMPLE_EDGE), Reducer 16 (SIMPLE_EDGE), Union 3 (CONTAINS) Map 13 <- Union 14 (CONTAINS) Map 5 <- Union 6 (CONTAINS) Reducer 4 <- Union 3 (SIMPLE_EDGE) Reducer 7 <- Union 6 (SIMPLE_EDGE) Map 9 <- Union 6 (CONTAINS) Reducer 8 <- Map 10 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) Reducer 15 <- Union 14 (SIMPLE_EDGE) Reducer 16 <- Map 18 (SIMPLE_EDGE), Reducer 15 (SIMPLE_EDGE) Map 17 <- Union 14 (CONTAINS) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 4 File Output Operator [FS_61] compressed:false Statistics:Num rows: 275 Data size: 2921 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_59] | keys:KEY._col0 (type: string), KEY._col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE |<-Union 3 [SIMPLE_EDGE] |<-Reducer 2 [CONTAINS] | Reduce Output Operator [RS_58] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Group By Operator [GBY_57] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Select Operator [SEL_26] | outputColumnNames:["_col0","_col1"] | Merge Join Operator [MERGEJOIN_85] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"1":"_col1 (type: string)","0":"_col0 (type: string)"} | | outputColumnNames:["_col1","_col2"] | |<-Map 1 [SIMPLE_EDGE] | | Reduce Output Operator [RS_22] | | key expressions:_col0 (type: string) | | Map-reduce partition columns:_col0 (type: string) | | sort order:+ | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | | Select Operator [SEL_1] | | outputColumnNames:["_col0"] | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | | Filter Operator [FIL_76] | | predicate:key is not null (type: boolean) | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | | TableScan [TS_0] | | alias:y | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | |<-Reducer 8 [SIMPLE_EDGE] | Reduce Output Operator [RS_24] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ | Statistics:Num rows: 144 Data size: 1509 Basic stats: COMPLETE Column stats: NONE | value expressions:_col0 (type: string) | Merge Join Operator [MERGEJOIN_84] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"1":"_col1 (type: string)","0":"_col0 (type: string)"} | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 144 Data size: 1509 Basic stats: COMPLETE Column stats: NONE | |<-Map 10 [SIMPLE_EDGE] | | Reduce Output Operator [RS_18] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col0 (type: string) | | Select Operator [SEL_14] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | Filter Operator [FIL_79] | | predicate:(value is not null and key is not null) (type: boolean) | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | TableScan [TS_13] | | alias:x | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | |<-Reducer 7 [SIMPLE_EDGE] | Reduce Output Operator [RS_16] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE | Select Operator [SEL_12] | outputColumnNames:["_col0"] | Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE | Group By Operator [GBY_11] | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE | |<-Union 6 [SIMPLE_EDGE] | |<-Map 5 [CONTAINS] | | Reduce Output Operator [RS_10] | | key expressions:_col0 (type: string), _col1 (type: string) | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | sort order:++ | | Group By Operator [GBY_9] | | keys:_col0 (type: string), _col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Select Operator [SEL_3] | | outputColumnNames:["_col0","_col1"] | | Filter Operator [FIL_77] | | predicate:value is not null (type: boolean) | | TableScan [TS_2] | | alias:x | |<-Map 9 [CONTAINS] | Reduce Output Operator [RS_10] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Group By Operator [GBY_9] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Select Operator [SEL_5] | outputColumnNames:["_col0","_col1"] | Filter Operator [FIL_78] | predicate:value is not null (type: boolean) | TableScan [TS_4] | alias:y |<-Reducer 12 [CONTAINS] Reduce Output Operator [RS_58] key expressions:_col0 (type: string), _col1 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string) sort order:++ Group By Operator [GBY_57] keys:_col0 (type: string), _col1 (type: string) outputColumnNames:["_col0","_col1"] Select Operator [SEL_53] outputColumnNames:["_col0","_col1"] Merge Join Operator [MERGEJOIN_87] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"1":"_col1 (type: string)","0":"_col0 (type: string)"} | outputColumnNames:["_col1","_col2"] |<-Map 11 [SIMPLE_EDGE] | Reduce Output Operator [RS_49] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | Select Operator [SEL_28] | outputColumnNames:["_col0"] | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | Filter Operator [FIL_80] | predicate:key is not null (type: boolean) | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_27] | alias:y | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE |<-Reducer 16 [SIMPLE_EDGE] Reduce Output Operator [RS_51] key expressions:_col1 (type: string) Map-reduce partition columns:_col1 (type: string) sort order:+ Statistics:Num rows: 144 Data size: 1509 Basic stats: COMPLETE Column stats: NONE value expressions:_col0 (type: string) Merge Join Operator [MERGEJOIN_86] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"1":"_col1 (type: string)","0":"_col0 (type: string)"} | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 144 Data size: 1509 Basic stats: COMPLETE Column stats: NONE |<-Map 18 [SIMPLE_EDGE] | Reduce Output Operator [RS_45] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | value expressions:_col0 (type: string) | Select Operator [SEL_41] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | Filter Operator [FIL_83] | predicate:(value is not null and key is not null) (type: boolean) | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_40] | alias:x | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE |<-Reducer 15 [SIMPLE_EDGE] Reduce Output Operator [RS_43] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE Select Operator [SEL_39] outputColumnNames:["_col0"] Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE Group By Operator [GBY_38] | keys:KEY._col0 (type: string), KEY._col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE |<-Union 14 [SIMPLE_EDGE] |<-Map 13 [CONTAINS] | Reduce Output Operator [RS_37] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Group By Operator [GBY_36] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Select Operator [SEL_30] | outputColumnNames:["_col0","_col1"] | Filter Operator [FIL_81] | predicate:value is not null (type: boolean) | TableScan [TS_29] | alias:x |<-Map 17 [CONTAINS] Reduce Output Operator [RS_37] key expressions:_col0 (type: string), _col1 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string) sort order:++ Group By Operator [GBY_36] keys:_col0 (type: string), _col1 (type: string) outputColumnNames:["_col0","_col1"] Select Operator [SEL_32] outputColumnNames:["_col0","_col1"] Filter Operator [FIL_82] predicate:value is not null (type: boolean) TableScan [TS_31] alias:y PREHOOK: query: explain SELECT x.key, y.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN (select * from src1 union select * from src)z ON (x.value = z.value) union SELECT x.key, y.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN (select key, value from src1 union select key, value from src union select key, value from src)z ON (x.value = z.value) union SELECT x.key, y.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN (select key, value from src1 union select key, value from src union select key, value from src union select key, value from src)z ON (x.value = z.value) PREHOOK: type: QUERY POSTHOOK: query: explain SELECT x.key, y.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN (select * from src1 union select * from src)z ON (x.value = z.value) union SELECT x.key, y.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN (select key, value from src1 union select key, value from src union select key, value from src)z ON (x.value = z.value) union SELECT x.key, y.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN (select key, value from src1 union select key, value from src union select key, value from src union select key, value from src)z ON (x.value = z.value) POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 32 <- Union 31 (SIMPLE_EDGE) Map 11 <- Union 8 (CONTAINS) Reducer 14 <- Map 13 (SIMPLE_EDGE), Reducer 20 (SIMPLE_EDGE), Union 3 (CONTAINS) Reducer 30 <- Union 29 (SIMPLE_EDGE), Union 31 (CONTAINS) Reducer 25 <- Map 24 (SIMPLE_EDGE), Reducer 33 (SIMPLE_EDGE), Union 5 (CONTAINS) Map 22 <- Union 18 (CONTAINS) Map 21 <- Union 16 (CONTAINS) Map 34 <- Union 27 (CONTAINS) Reducer 10 <- Map 12 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) Reducer 33 <- Map 37 (SIMPLE_EDGE), Reducer 32 (SIMPLE_EDGE) Reducer 20 <- Map 23 (SIMPLE_EDGE), Reducer 19 (SIMPLE_EDGE) Map 36 <- Union 31 (CONTAINS) Map 35 <- Union 29 (CONTAINS) Reducer 4 <- Union 3 (SIMPLE_EDGE), Union 5 (CONTAINS) Reducer 19 <- Union 18 (SIMPLE_EDGE) Reducer 6 <- Union 5 (SIMPLE_EDGE) Reducer 9 <- Union 8 (SIMPLE_EDGE) Reducer 17 <- Union 16 (SIMPLE_EDGE), Union 18 (CONTAINS) Map 15 <- Union 16 (CONTAINS) Reducer 28 <- Union 27 (SIMPLE_EDGE), Union 29 (CONTAINS) Map 26 <- Union 27 (CONTAINS) Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 10 (SIMPLE_EDGE), Union 3 (CONTAINS) Map 7 <- Union 8 (CONTAINS) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 6 File Output Operator [FS_122] compressed:false Statistics:Num rows: 275 Data size: 2921 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_120] | keys:KEY._col0 (type: string), KEY._col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE |<-Union 5 [SIMPLE_EDGE] |<-Reducer 25 [CONTAINS] | Reduce Output Operator [RS_119] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Group By Operator [GBY_118] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Select Operator [SEL_114] | outputColumnNames:["_col0","_col1"] | Merge Join Operator [MERGEJOIN_170] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"1":"_col1 (type: string)","0":"_col0 (type: string)"} | | outputColumnNames:["_col1","_col3"] | |<-Map 24 [SIMPLE_EDGE] | | Reduce Output Operator [RS_110] | | key expressions:_col0 (type: string) | | Map-reduce partition columns:_col0 (type: string) | | sort order:+ | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col1 (type: string) | | Select Operator [SEL_71] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | | Filter Operator [FIL_159] | | predicate:key is not null (type: boolean) | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | | TableScan [TS_70] | | alias:y | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | |<-Reducer 33 [SIMPLE_EDGE] | Reduce Output Operator [RS_112] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ | Statistics:Num rows: 242 Data size: 2565 Basic stats: COMPLETE Column stats: NONE | Merge Join Operator [MERGEJOIN_169] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"1":"_col1 (type: string)","0":"_col0 (type: string)"} | | outputColumnNames:["_col1"] | | Statistics:Num rows: 242 Data size: 2565 Basic stats: COMPLETE Column stats: NONE | |<-Map 37 [SIMPLE_EDGE] | | Reduce Output Operator [RS_106] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col0 (type: string) | | Select Operator [SEL_102] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | Filter Operator [FIL_164] | | predicate:(value is not null and key is not null) (type: boolean) | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | TableScan [TS_101] | | alias:x | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | |<-Reducer 32 [SIMPLE_EDGE] | Reduce Output Operator [RS_104] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 220 Data size: 2332 Basic stats: COMPLETE Column stats: NONE | Select Operator [SEL_100] | outputColumnNames:["_col0"] | Statistics:Num rows: 220 Data size: 2332 Basic stats: COMPLETE Column stats: NONE | Group By Operator [GBY_99] | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 220 Data size: 2332 Basic stats: COMPLETE Column stats: NONE | |<-Union 31 [SIMPLE_EDGE] | |<-Reducer 30 [CONTAINS] | | Reduce Output Operator [RS_98] | | key expressions:_col0 (type: string), _col1 (type: string) | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | sort order:++ | | Group By Operator [GBY_97] | | keys:_col0 (type: string), _col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Group By Operator [GBY_90] | | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | | outputColumnNames:["_col0","_col1"] | | |<-Union 29 [SIMPLE_EDGE] | | |<-Map 35 [CONTAINS] | | | Reduce Output Operator [RS_89] | | | key expressions:_col0 (type: string), _col1 (type: string) | | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | | sort order:++ | | | Group By Operator [GBY_88] | | | keys:_col0 (type: string), _col1 (type: string) | | | outputColumnNames:["_col0","_col1"] | | | Select Operator [SEL_84] | | | outputColumnNames:["_col0","_col1"] | | | Filter Operator [FIL_162] | | | predicate:value is not null (type: boolean) | | | TableScan [TS_83] | | | alias:y | | |<-Reducer 28 [CONTAINS] | | Reduce Output Operator [RS_89] | | key expressions:_col0 (type: string), _col1 (type: string) | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | sort order:++ | | Group By Operator [GBY_88] | | keys:_col0 (type: string), _col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Group By Operator [GBY_81] | | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | | outputColumnNames:["_col0","_col1"] | | |<-Union 27 [SIMPLE_EDGE] | | |<-Map 34 [CONTAINS] | | | Reduce Output Operator [RS_80] | | | key expressions:_col0 (type: string), _col1 (type: string) | | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | | sort order:++ | | | Group By Operator [GBY_79] | | | keys:_col0 (type: string), _col1 (type: string) | | | outputColumnNames:["_col0","_col1"] | | | Select Operator [SEL_75] | | | outputColumnNames:["_col0","_col1"] | | | Filter Operator [FIL_161] | | | predicate:value is not null (type: boolean) | | | TableScan [TS_74] | | | alias:y | | |<-Map 26 [CONTAINS] | | Reduce Output Operator [RS_80] | | key expressions:_col0 (type: string), _col1 (type: string) | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | sort order:++ | | Group By Operator [GBY_79] | | keys:_col0 (type: string), _col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Select Operator [SEL_73] | | outputColumnNames:["_col0","_col1"] | | Filter Operator [FIL_160] | | predicate:value is not null (type: boolean) | | TableScan [TS_72] | | alias:x | |<-Map 36 [CONTAINS] | Reduce Output Operator [RS_98] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Group By Operator [GBY_97] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Select Operator [SEL_93] | outputColumnNames:["_col0","_col1"] | Filter Operator [FIL_163] | predicate:value is not null (type: boolean) | TableScan [TS_92] | alias:y |<-Reducer 4 [CONTAINS] Reduce Output Operator [RS_119] key expressions:_col0 (type: string), _col1 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string) sort order:++ Group By Operator [GBY_118] keys:_col0 (type: string), _col1 (type: string) outputColumnNames:["_col0","_col1"] Group By Operator [GBY_68] | keys:KEY._col0 (type: string), KEY._col1 (type: string) | outputColumnNames:["_col0","_col1"] |<-Union 3 [SIMPLE_EDGE] |<-Reducer 14 [CONTAINS] | Reduce Output Operator [RS_67] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Group By Operator [GBY_66] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Select Operator [SEL_62] | outputColumnNames:["_col0","_col1"] | Merge Join Operator [MERGEJOIN_168] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"1":"_col1 (type: string)","0":"_col0 (type: string)"} | | outputColumnNames:["_col1","_col3"] | |<-Map 13 [SIMPLE_EDGE] | | Reduce Output Operator [RS_58] | | key expressions:_col0 (type: string) | | Map-reduce partition columns:_col0 (type: string) | | sort order:+ | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col1 (type: string) | | Select Operator [SEL_28] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | | Filter Operator [FIL_154] | | predicate:key is not null (type: boolean) | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | | TableScan [TS_27] | | alias:y | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | |<-Reducer 20 [SIMPLE_EDGE] | Reduce Output Operator [RS_60] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ | Statistics:Num rows: 209 Data size: 2208 Basic stats: COMPLETE Column stats: NONE | Merge Join Operator [MERGEJOIN_167] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"1":"_col1 (type: string)","0":"_col0 (type: string)"} | | outputColumnNames:["_col1"] | | Statistics:Num rows: 209 Data size: 2208 Basic stats: COMPLETE Column stats: NONE | |<-Map 23 [SIMPLE_EDGE] | | Reduce Output Operator [RS_54] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col0 (type: string) | | Select Operator [SEL_50] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | Filter Operator [FIL_158] | | predicate:(value is not null and key is not null) (type: boolean) | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | TableScan [TS_49] | | alias:x | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | |<-Reducer 19 [SIMPLE_EDGE] | Reduce Output Operator [RS_52] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 190 Data size: 2008 Basic stats: COMPLETE Column stats: NONE | Select Operator [SEL_48] | outputColumnNames:["_col0"] | Statistics:Num rows: 190 Data size: 2008 Basic stats: COMPLETE Column stats: NONE | Group By Operator [GBY_47] | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 190 Data size: 2008 Basic stats: COMPLETE Column stats: NONE | |<-Union 18 [SIMPLE_EDGE] | |<-Map 22 [CONTAINS] | | Reduce Output Operator [RS_46] | | key expressions:_col0 (type: string), _col1 (type: string) | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | sort order:++ | | Group By Operator [GBY_45] | | keys:_col0 (type: string), _col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Select Operator [SEL_41] | | outputColumnNames:["_col0","_col1"] | | Filter Operator [FIL_157] | | predicate:value is not null (type: boolean) | | TableScan [TS_40] | | alias:y | |<-Reducer 17 [CONTAINS] | Reduce Output Operator [RS_46] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Group By Operator [GBY_45] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Group By Operator [GBY_38] | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | outputColumnNames:["_col0","_col1"] | |<-Union 16 [SIMPLE_EDGE] | |<-Map 21 [CONTAINS] | | Reduce Output Operator [RS_37] | | key expressions:_col0 (type: string), _col1 (type: string) | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | sort order:++ | | Group By Operator [GBY_36] | | keys:_col0 (type: string), _col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Select Operator [SEL_32] | | outputColumnNames:["_col0","_col1"] | | Filter Operator [FIL_156] | | predicate:value is not null (type: boolean) | | TableScan [TS_31] | | alias:y | |<-Map 15 [CONTAINS] | Reduce Output Operator [RS_37] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Group By Operator [GBY_36] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Select Operator [SEL_30] | outputColumnNames:["_col0","_col1"] | Filter Operator [FIL_155] | predicate:value is not null (type: boolean) | TableScan [TS_29] | alias:x |<-Reducer 2 [CONTAINS] Reduce Output Operator [RS_67] key expressions:_col0 (type: string), _col1 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string) sort order:++ Group By Operator [GBY_66] keys:_col0 (type: string), _col1 (type: string) outputColumnNames:["_col0","_col1"] Select Operator [SEL_26] outputColumnNames:["_col0","_col1"] Merge Join Operator [MERGEJOIN_166] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"1":"_col1 (type: string)","0":"_col0 (type: string)"} | outputColumnNames:["_col1","_col3"] |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_22] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | value expressions:_col1 (type: string) | Select Operator [SEL_1] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | Filter Operator [FIL_150] | predicate:key is not null (type: boolean) | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_0] | alias:y | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE |<-Reducer 10 [SIMPLE_EDGE] Reduce Output Operator [RS_24] key expressions:_col1 (type: string) Map-reduce partition columns:_col1 (type: string) sort order:+ Statistics:Num rows: 144 Data size: 1509 Basic stats: COMPLETE Column stats: NONE Merge Join Operator [MERGEJOIN_165] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"1":"_col1 (type: string)","0":"_col0 (type: string)"} | outputColumnNames:["_col1"] | Statistics:Num rows: 144 Data size: 1509 Basic stats: COMPLETE Column stats: NONE |<-Map 12 [SIMPLE_EDGE] | Reduce Output Operator [RS_18] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | value expressions:_col0 (type: string) | Select Operator [SEL_14] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | Filter Operator [FIL_153] | predicate:(value is not null and key is not null) (type: boolean) | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_13] | alias:x | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE |<-Reducer 9 [SIMPLE_EDGE] Reduce Output Operator [RS_16] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE Select Operator [SEL_12] outputColumnNames:["_col0"] Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE Group By Operator [GBY_11] | keys:KEY._col0 (type: string), KEY._col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE |<-Union 8 [SIMPLE_EDGE] |<-Map 11 [CONTAINS] | Reduce Output Operator [RS_10] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Group By Operator [GBY_9] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Select Operator [SEL_5] | outputColumnNames:["_col0","_col1"] | Filter Operator [FIL_152] | predicate:value is not null (type: boolean) | TableScan [TS_4] | alias:y |<-Map 7 [CONTAINS] Reduce Output Operator [RS_10] key expressions:_col0 (type: string), _col1 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string) sort order:++ Group By Operator [GBY_9] keys:_col0 (type: string), _col1 (type: string) outputColumnNames:["_col0","_col1"] Select Operator [SEL_3] outputColumnNames:["_col0","_col1"] Filter Operator [FIL_151] predicate:value is not null (type: boolean) TableScan [TS_2] alias:x PREHOOK: query: EXPLAIN SELECT x.key, z.value, y.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN srcpart z ON (x.value = z.value and z.ds='2008-04-08' and z.hr=11) PREHOOK: type: QUERY POSTHOOK: query: EXPLAIN SELECT x.key, z.value, y.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN srcpart z ON (x.value = z.value and z.ds='2008-04-08' and z.hr=11) POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Map 2 <- Map 1 (BROADCAST_EDGE), Map 3 (BROADCAST_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Map 2 File Output Operator [FS_19] compressed:false Statistics:Num rows: 302 Data size: 3213 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_18] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE Map Join Operator [MAPJOIN_29] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"Map 1":"_col0 (type: string)","Map 2":"_col3 (type: string)"} | outputColumnNames:["_col0","_col4","_col5"] | Statistics:Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [BROADCAST_EDGE] | Reduce Output Operator [RS_14] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | Select Operator [SEL_2] | outputColumnNames:["_col0"] | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | Filter Operator [FIL_25] | predicate:value is not null (type: boolean) | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_0] | alias:z | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE |<-Map Join Operator [MAPJOIN_28] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"Map 2":"_col0 (type: string)","Map 3":"_col0 (type: string)"} | outputColumnNames:["_col1","_col2","_col3"] | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE |<-Map 3 [BROADCAST_EDGE] | Reduce Output Operator [RS_10] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | value expressions:_col1 (type: string) | Select Operator [SEL_6] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | Filter Operator [FIL_27] | predicate:(key is not null and value is not null) (type: boolean) | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_5] | alias:x | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE |<-Select Operator [SEL_4] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Filter Operator [FIL_26] predicate:key is not null (type: boolean) Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan [TS_3] alias:y Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: EXPLAIN select ss.k1,sr.k2,cs.k3,count(ss.v1),count(sr.v2),count(cs.v3) FROM ss,sr,cs,src d1,src d2,src d3,src1,srcpart where ss.k1 = d1.key and sr.k1 = d2.key and cs.k1 = d3.key and ss.k2 = sr.k2 and ss.k3 = sr.k3 and ss.v1 = src1.value and ss.v2 = srcpart.value and sr.v2 = cs.v2 and sr.v3 = cs.v3 and ss.v3='ssv3' and sr.v1='srv1' and src1.key = 'src1key' and srcpart.key = 'srcpartkey' and d1.value = 'd1value' and d2.value in ('2000Q1','2000Q2','2000Q3') and d3.value in ('2000Q1','2000Q2','2000Q3') group by ss.k1,sr.k2,cs.k3 order by ss.k1,sr.k2,cs.k3 limit 100 PREHOOK: type: QUERY POSTHOOK: query: EXPLAIN select ss.k1,sr.k2,cs.k3,count(ss.v1),count(sr.v2),count(cs.v3) FROM ss,sr,cs,src d1,src d2,src d3,src1,srcpart where ss.k1 = d1.key and sr.k1 = d2.key and cs.k1 = d3.key and ss.k2 = sr.k2 and ss.k3 = sr.k3 and ss.v1 = src1.value and ss.v2 = srcpart.value and sr.v2 = cs.v2 and sr.v3 = cs.v3 and ss.v3='ssv3' and sr.v1='srv1' and src1.key = 'src1key' and srcpart.key = 'srcpartkey' and d1.value = 'd1value' and d2.value in ('2000Q1','2000Q2','2000Q3') and d3.value in ('2000Q1','2000Q2','2000Q3') group by ss.k1,sr.k2,cs.k3 order by ss.k1,sr.k2,cs.k3 limit 100 POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Map 2 <- Map 1 (BROADCAST_EDGE), Map 4 (BROADCAST_EDGE) Map 4 <- Map 3 (BROADCAST_EDGE) Map 7 <- Map 10 (BROADCAST_EDGE), Map 2 (BROADCAST_EDGE), Map 5 (BROADCAST_EDGE), Map 6 (BROADCAST_EDGE) Reducer 9 <- Reducer 8 (SIMPLE_EDGE) Reducer 8 <- Map 7 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 Reducer 9 File Output Operator [FS_71] compressed:false Statistics:Num rows: 100 Data size: 1000 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_70] Number of rows:100 Statistics:Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE Select Operator [SEL_69] | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] | Statistics:Num rows: 365 Data size: 3882 Basic stats: COMPLETE Column stats: NONE |<-Reducer 8 [SIMPLE_EDGE] Reduce Output Operator [RS_68] key expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string) sort order:+++ Statistics:Num rows: 365 Data size: 3882 Basic stats: COMPLETE Column stats: NONE value expressions:_col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint) Group By Operator [GBY_66] | aggregations:["count(VALUE._col0)","count(VALUE._col1)","count(VALUE._col2)"] | keys:KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] | Statistics:Num rows: 365 Data size: 3882 Basic stats: COMPLETE Column stats: NONE |<-Map 7 [SIMPLE_EDGE] Reduce Output Operator [RS_65] key expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string), _col2 (type: string) sort order:+++ Statistics:Num rows: 731 Data size: 7775 Basic stats: COMPLETE Column stats: NONE value expressions:_col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint) Group By Operator [GBY_64] aggregations:["count(_col3)","count(_col4)","count(_col5)"] keys:_col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] Statistics:Num rows: 731 Data size: 7775 Basic stats: COMPLETE Column stats: NONE Select Operator [SEL_62] outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] Statistics:Num rows: 731 Data size: 7775 Basic stats: COMPLETE Column stats: NONE Map Join Operator [MAPJOIN_111] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"Map 2":"_col8 (type: string), _col10 (type: string)","Map 7":"_col8 (type: string), _col10 (type: string)"} | outputColumnNames:["_col2","_col3","_col8","_col9","_col20","_col21"] | Statistics:Num rows: 731 Data size: 7775 Basic stats: COMPLETE Column stats: NONE |<-Map 2 [BROADCAST_EDGE] | Reduce Output Operator [RS_58] | key expressions:_col8 (type: string), _col10 (type: string) | Map-reduce partition columns:_col8 (type: string), _col10 (type: string) | sort order:++ | Statistics:Num rows: 150 Data size: 1606 Basic stats: COMPLETE Column stats: NONE | value expressions:_col2 (type: string), _col3 (type: string), _col9 (type: string) | Map Join Operator [MAPJOIN_110] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"Map 2":"_col1 (type: string), _col3 (type: string)","Map 4":"_col3 (type: string), _col5 (type: string)"} | | outputColumnNames:["_col2","_col3","_col8","_col9","_col10"] | | Statistics:Num rows: 150 Data size: 1606 Basic stats: COMPLETE Column stats: NONE | |<-Map 4 [BROADCAST_EDGE] | | Reduce Output Operator [RS_55] | | key expressions:_col3 (type: string), _col5 (type: string) | | Map-reduce partition columns:_col3 (type: string), _col5 (type: string) | | sort order:++ | | Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col2 (type: string), _col4 (type: string) | | Map Join Operator [MAPJOIN_106] | | | condition map:[{"":"Inner Join 0 to 1"}] | | | keys:{"Map 3":"_col0 (type: string)","Map 4":"_col0 (type: string)"} | | | outputColumnNames:["_col2","_col3","_col4","_col5"] | | | Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE | | |<-Map 3 [BROADCAST_EDGE] | | | Reduce Output Operator [RS_12] | | | key expressions:_col0 (type: string) | | | Map-reduce partition columns:_col0 (type: string) | | | sort order:+ | | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE | | | value expressions:_col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) | | | Select Operator [SEL_7] | | | outputColumnNames:["_col0","_col2","_col3","_col4","_col5"] | | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE | | | Filter Operator [FIL_99] | | | predicate:((((((v1 = 'srv1') and k1 is not null) and v2 is not null) and v3 is not null) and k2 is not null) and k3 is not null) (type: boolean) | | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE | | | TableScan [TS_5] | | | alias:sr | | | Statistics:Num rows: 85 Data size: 2945 Basic stats: COMPLETE Column stats: NONE | | |<-Select Operator [SEL_10] | | outputColumnNames:["_col0"] | | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE | | Filter Operator [FIL_100] | | predicate:((value) IN ('2000Q1', '2000Q2', '2000Q3') and key is not null) (type: boolean) | | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE | | TableScan [TS_8] | | alias:d1 | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | |<-Map Join Operator [MAPJOIN_105] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"Map 1":"_col0 (type: string)","Map 2":"_col0 (type: string)"} | | outputColumnNames:["_col1","_col2","_col3"] | | Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE | |<-Map 1 [BROADCAST_EDGE] | | Reduce Output Operator [RS_48] | | key expressions:_col0 (type: string) | | Map-reduce partition columns:_col0 (type: string) | | sort order:+ | | Statistics:Num rows: 22 Data size: 762 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col1 (type: string), _col2 (type: string), _col3 (type: string) | | Select Operator [SEL_1] | | outputColumnNames:["_col0","_col1","_col2","_col3"] | | Statistics:Num rows: 22 Data size: 762 Basic stats: COMPLETE Column stats: NONE | | Filter Operator [FIL_97] | | predicate:((k1 is not null and v2 is not null) and v3 is not null) (type: boolean) | | Statistics:Num rows: 22 Data size: 762 Basic stats: COMPLETE Column stats: NONE | | TableScan [TS_0] | | alias:cs | | Statistics:Num rows: 170 Data size: 5890 Basic stats: COMPLETE Column stats: NONE | |<-Select Operator [SEL_4] | outputColumnNames:["_col0"] | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE | Filter Operator [FIL_98] | predicate:((value) IN ('2000Q1', '2000Q2', '2000Q3') and key is not null) (type: boolean) | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_2] | alias:d1 | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE |<-Select Operator [SEL_46] outputColumnNames:["_col10","_col6","_col7","_col8"] Statistics:Num rows: 665 Data size: 7069 Basic stats: COMPLETE Column stats: NONE Map Join Operator [MAPJOIN_109] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"Map 5":"_col1 (type: string)","Map 7":"_col5 (type: string)"} | outputColumnNames:["_col6","_col7","_col8","_col10"] | Statistics:Num rows: 665 Data size: 7069 Basic stats: COMPLETE Column stats: NONE |<-Map 5 [BROADCAST_EDGE] | Reduce Output Operator [RS_42] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ | Statistics:Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE | Select Operator [SEL_19] | outputColumnNames:["_col1"] | Statistics:Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE | Filter Operator [FIL_101] | predicate:((key = 'src1key') and value is not null) (type: boolean) | Statistics:Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_17] | alias:src1 | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE |<-Map Join Operator [MAPJOIN_108] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"Map 7":"_col2 (type: string)","Map 6":"_col0 (type: string)"} | outputColumnNames:["_col4","_col5","_col6","_col8"] | Statistics:Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE |<-Map 6 [BROADCAST_EDGE] | Reduce Output Operator [RS_36] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE | Select Operator [SEL_22] | outputColumnNames:["_col0"] | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE | Filter Operator [FIL_102] | predicate:((value = 'd1value') and key is not null) (type: boolean) | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_20] | alias:d1 | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE |<-Map Join Operator [MAPJOIN_107] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"Map 10":"_col3 (type: string)","Map 7":"_col1 (type: string)"} | outputColumnNames:["_col2","_col3","_col4","_col6"] | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE |<-Map 10 [BROADCAST_EDGE] | Reduce Output Operator [RS_32] | key expressions:_col3 (type: string) | Map-reduce partition columns:_col3 (type: string) | sort order:+ | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE | value expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string), _col4 (type: string) | Select Operator [SEL_28] | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE | Filter Operator [FIL_104] | predicate:((((((v3 = 'ssv3') and v2 is not null) and k1 is not null) and v1 is not null) and k2 is not null) and k3 is not null) (type: boolean) | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_26] | alias:ss | Statistics:Num rows: 85 Data size: 2945 Basic stats: COMPLETE Column stats: NONE |<-Select Operator [SEL_25] outputColumnNames:["_col1"] Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator [FIL_103] predicate:((key = 'srcpartkey') and value is not null) (type: boolean) Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE TableScan [TS_23] alias:srcpart Statistics:Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: explain SELECT x.key, z.value, y.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN (select * from src1 union select * from src)z ON (x.value = z.value) union SELECT x.key, z.value, y.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN (select * from src1 union select * from src)z ON (x.value = z.value) PREHOOK: type: QUERY POSTHOOK: query: explain SELECT x.key, z.value, y.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN (select * from src1 union select * from src)z ON (x.value = z.value) union SELECT x.key, z.value, y.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN (select * from src1 union select * from src)z ON (x.value = z.value) POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 3 <- Union 2 (SIMPLE_EDGE) Reducer 12 <- Map 14 (BROADCAST_EDGE), Union 11 (SIMPLE_EDGE) Map 13 <- Union 11 (CONTAINS) Map 1 <- Reducer 6 (BROADCAST_EDGE), Union 2 (CONTAINS) Map 10 <- Union 11 (CONTAINS) Map 4 <- Union 5 (CONTAINS) Map 7 <- Union 5 (CONTAINS) Reducer 6 <- Map 8 (BROADCAST_EDGE), Union 5 (SIMPLE_EDGE) Map 9 <- Reducer 12 (BROADCAST_EDGE), Union 2 (CONTAINS) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 3 File Output Operator [FS_61] compressed:false Statistics:Num rows: 275 Data size: 2921 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_59] | keys:KEY._col0 (type: string), KEY._col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE |<-Union 2 [SIMPLE_EDGE] |<-Map 1 [CONTAINS] | Reduce Output Operator [RS_58] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Group By Operator [GBY_57] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Select Operator [SEL_26] | outputColumnNames:["_col0","_col1"] | Map Join Operator [MAPJOIN_85] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"Map 1":"_col0 (type: string)","Reducer 6":"_col1 (type: string)"} | | outputColumnNames:["_col1","_col2"] | |<-Reducer 6 [BROADCAST_EDGE] | | Reduce Output Operator [RS_24] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ | | Statistics:Num rows: 144 Data size: 1509 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col0 (type: string) | | Map Join Operator [MAPJOIN_84] | | | condition map:[{"":"Inner Join 0 to 1"}] | | | keys:{"Reducer 6":"_col0 (type: string)","Map 8":"_col1 (type: string)"} | | | outputColumnNames:["_col0","_col1"] | | | Statistics:Num rows: 144 Data size: 1509 Basic stats: COMPLETE Column stats: NONE | | |<-Map 8 [BROADCAST_EDGE] | | | Reduce Output Operator [RS_18] | | | key expressions:_col1 (type: string) | | | Map-reduce partition columns:_col1 (type: string) | | | sort order:+ | | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | | value expressions:_col0 (type: string) | | | Select Operator [SEL_14] | | | outputColumnNames:["_col0","_col1"] | | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | | Filter Operator [FIL_79] | | | predicate:(value is not null and key is not null) (type: boolean) | | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | | TableScan [TS_13] | | | alias:x | | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | | |<-Select Operator [SEL_12] | | outputColumnNames:["_col0"] | | Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE | | Group By Operator [GBY_11] | | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | | outputColumnNames:["_col0","_col1"] | | | Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE | | |<-Union 5 [SIMPLE_EDGE] | | |<-Map 4 [CONTAINS] | | | Reduce Output Operator [RS_10] | | | key expressions:_col0 (type: string), _col1 (type: string) | | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | | sort order:++ | | | Group By Operator [GBY_9] | | | keys:_col0 (type: string), _col1 (type: string) | | | outputColumnNames:["_col0","_col1"] | | | Select Operator [SEL_3] | | | outputColumnNames:["_col0","_col1"] | | | Filter Operator [FIL_77] | | | predicate:value is not null (type: boolean) | | | TableScan [TS_2] | | | alias:x | | |<-Map 7 [CONTAINS] | | Reduce Output Operator [RS_10] | | key expressions:_col0 (type: string), _col1 (type: string) | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | sort order:++ | | Group By Operator [GBY_9] | | keys:_col0 (type: string), _col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Select Operator [SEL_5] | | outputColumnNames:["_col0","_col1"] | | Filter Operator [FIL_78] | | predicate:value is not null (type: boolean) | | TableScan [TS_4] | | alias:y | |<-Select Operator [SEL_1] | outputColumnNames:["_col0"] | Filter Operator [FIL_76] | predicate:key is not null (type: boolean) | TableScan [TS_0] | alias:y |<-Map 9 [CONTAINS] Reduce Output Operator [RS_58] key expressions:_col0 (type: string), _col1 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string) sort order:++ Group By Operator [GBY_57] keys:_col0 (type: string), _col1 (type: string) outputColumnNames:["_col0","_col1"] Select Operator [SEL_53] outputColumnNames:["_col0","_col1"] Map Join Operator [MAPJOIN_87] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"Reducer 12":"_col1 (type: string)","Map 9":"_col0 (type: string)"} | outputColumnNames:["_col1","_col2"] |<-Reducer 12 [BROADCAST_EDGE] | Reduce Output Operator [RS_51] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ | Statistics:Num rows: 144 Data size: 1509 Basic stats: COMPLETE Column stats: NONE | value expressions:_col0 (type: string) | Map Join Operator [MAPJOIN_86] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"Map 14":"_col1 (type: string)","Reducer 12":"_col0 (type: string)"} | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 144 Data size: 1509 Basic stats: COMPLETE Column stats: NONE | |<-Map 14 [BROADCAST_EDGE] | | Reduce Output Operator [RS_45] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col0 (type: string) | | Select Operator [SEL_41] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | Filter Operator [FIL_83] | | predicate:(value is not null and key is not null) (type: boolean) | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | TableScan [TS_40] | | alias:x | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | |<-Select Operator [SEL_39] | outputColumnNames:["_col0"] | Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE | Group By Operator [GBY_38] | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE | |<-Union 11 [SIMPLE_EDGE] | |<-Map 13 [CONTAINS] | | Reduce Output Operator [RS_37] | | key expressions:_col0 (type: string), _col1 (type: string) | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | sort order:++ | | Group By Operator [GBY_36] | | keys:_col0 (type: string), _col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Select Operator [SEL_32] | | outputColumnNames:["_col0","_col1"] | | Filter Operator [FIL_82] | | predicate:value is not null (type: boolean) | | TableScan [TS_31] | | alias:y | |<-Map 10 [CONTAINS] | Reduce Output Operator [RS_37] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Group By Operator [GBY_36] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Select Operator [SEL_30] | outputColumnNames:["_col0","_col1"] | Filter Operator [FIL_81] | predicate:value is not null (type: boolean) | TableScan [TS_29] | alias:x |<-Select Operator [SEL_28] outputColumnNames:["_col0"] Filter Operator [FIL_80] predicate:key is not null (type: boolean) TableScan [TS_27] alias:y PREHOOK: query: explain SELECT x.key, y.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN (select * from src1 union select * from src)z ON (x.value = z.value) union SELECT x.key, y.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN (select key, value from src1 union select key, value from src union select key, value from src)z ON (x.value = z.value) union SELECT x.key, y.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN (select key, value from src1 union select key, value from src union select key, value from src union select key, value from src)z ON (x.value = z.value) PREHOOK: type: QUERY POSTHOOK: query: explain SELECT x.key, y.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN (select * from src1 union select * from src)z ON (x.value = z.value) union SELECT x.key, y.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN (select key, value from src1 union select key, value from src union select key, value from src)z ON (x.value = z.value) union SELECT x.key, y.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN (select key, value from src1 union select key, value from src union select key, value from src union select key, value from src)z ON (x.value = z.value) POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Map 12 <- Union 13 (CONTAINS) Map 30 <- Union 26 (CONTAINS) Reducer 23 <- Union 22 (SIMPLE_EDGE), Union 24 (CONTAINS) Reducer 14 <- Union 13 (SIMPLE_EDGE), Union 15 (CONTAINS) Map 11 <- Reducer 16 (BROADCAST_EDGE), Union 2 (CONTAINS) Reducer 25 <- Union 24 (SIMPLE_EDGE), Union 26 (CONTAINS) Map 21 <- Union 22 (CONTAINS) Map 1 <- Reducer 8 (BROADCAST_EDGE), Union 2 (CONTAINS) Map 20 <- Reducer 27 (BROADCAST_EDGE), Union 4 (CONTAINS) Reducer 5 <- Union 4 (SIMPLE_EDGE) Map 29 <- Union 24 (CONTAINS) Reducer 8 <- Map 10 (BROADCAST_EDGE), Union 7 (SIMPLE_EDGE) Reducer 27 <- Map 31 (BROADCAST_EDGE), Union 26 (SIMPLE_EDGE) Map 28 <- Union 22 (CONTAINS) Map 18 <- Union 15 (CONTAINS) Reducer 16 <- Map 19 (BROADCAST_EDGE), Union 15 (SIMPLE_EDGE) Map 17 <- Union 13 (CONTAINS) Reducer 3 <- Union 2 (SIMPLE_EDGE), Union 4 (CONTAINS) Map 6 <- Union 7 (CONTAINS) Map 9 <- Union 7 (CONTAINS) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 5 File Output Operator [FS_122] compressed:false Statistics:Num rows: 275 Data size: 2921 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_120] | keys:KEY._col0 (type: string), KEY._col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE |<-Union 4 [SIMPLE_EDGE] |<-Map 20 [CONTAINS] | Reduce Output Operator [RS_119] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Group By Operator [GBY_118] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Select Operator [SEL_114] | outputColumnNames:["_col0","_col1"] | Map Join Operator [MAPJOIN_170] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"Map 20":"_col0 (type: string)","Reducer 27":"_col1 (type: string)"} | | outputColumnNames:["_col1","_col3"] | |<-Reducer 27 [BROADCAST_EDGE] | | Reduce Output Operator [RS_112] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ | | Statistics:Num rows: 242 Data size: 2565 Basic stats: COMPLETE Column stats: NONE | | Map Join Operator [MAPJOIN_169] | | | condition map:[{"":"Inner Join 0 to 1"}] | | | keys:{"Map 31":"_col1 (type: string)","Reducer 27":"_col0 (type: string)"} | | | outputColumnNames:["_col1"] | | | Statistics:Num rows: 242 Data size: 2565 Basic stats: COMPLETE Column stats: NONE | | |<-Map 31 [BROADCAST_EDGE] | | | Reduce Output Operator [RS_106] | | | key expressions:_col1 (type: string) | | | Map-reduce partition columns:_col1 (type: string) | | | sort order:+ | | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | | value expressions:_col0 (type: string) | | | Select Operator [SEL_102] | | | outputColumnNames:["_col0","_col1"] | | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | | Filter Operator [FIL_164] | | | predicate:(value is not null and key is not null) (type: boolean) | | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | | TableScan [TS_101] | | | alias:x | | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | | |<-Select Operator [SEL_100] | | outputColumnNames:["_col0"] | | Statistics:Num rows: 220 Data size: 2332 Basic stats: COMPLETE Column stats: NONE | | Group By Operator [GBY_99] | | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | | outputColumnNames:["_col0","_col1"] | | | Statistics:Num rows: 220 Data size: 2332 Basic stats: COMPLETE Column stats: NONE | | |<-Union 26 [SIMPLE_EDGE] | | |<-Map 30 [CONTAINS] | | | Reduce Output Operator [RS_98] | | | key expressions:_col0 (type: string), _col1 (type: string) | | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | | sort order:++ | | | Group By Operator [GBY_97] | | | keys:_col0 (type: string), _col1 (type: string) | | | outputColumnNames:["_col0","_col1"] | | | Select Operator [SEL_93] | | | outputColumnNames:["_col0","_col1"] | | | Filter Operator [FIL_163] | | | predicate:value is not null (type: boolean) | | | TableScan [TS_92] | | | alias:y | | |<-Reducer 25 [CONTAINS] | | Reduce Output Operator [RS_98] | | key expressions:_col0 (type: string), _col1 (type: string) | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | sort order:++ | | Group By Operator [GBY_97] | | keys:_col0 (type: string), _col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Group By Operator [GBY_90] | | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | | outputColumnNames:["_col0","_col1"] | | |<-Union 24 [SIMPLE_EDGE] | | |<-Reducer 23 [CONTAINS] | | | Reduce Output Operator [RS_89] | | | key expressions:_col0 (type: string), _col1 (type: string) | | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | | sort order:++ | | | Group By Operator [GBY_88] | | | keys:_col0 (type: string), _col1 (type: string) | | | outputColumnNames:["_col0","_col1"] | | | Group By Operator [GBY_81] | | | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | | | outputColumnNames:["_col0","_col1"] | | | |<-Union 22 [SIMPLE_EDGE] | | | |<-Map 21 [CONTAINS] | | | | Reduce Output Operator [RS_80] | | | | key expressions:_col0 (type: string), _col1 (type: string) | | | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | | | sort order:++ | | | | Group By Operator [GBY_79] | | | | keys:_col0 (type: string), _col1 (type: string) | | | | outputColumnNames:["_col0","_col1"] | | | | Select Operator [SEL_73] | | | | outputColumnNames:["_col0","_col1"] | | | | Filter Operator [FIL_160] | | | | predicate:value is not null (type: boolean) | | | | TableScan [TS_72] | | | | alias:x | | | |<-Map 28 [CONTAINS] | | | Reduce Output Operator [RS_80] | | | key expressions:_col0 (type: string), _col1 (type: string) | | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | | sort order:++ | | | Group By Operator [GBY_79] | | | keys:_col0 (type: string), _col1 (type: string) | | | outputColumnNames:["_col0","_col1"] | | | Select Operator [SEL_75] | | | outputColumnNames:["_col0","_col1"] | | | Filter Operator [FIL_161] | | | predicate:value is not null (type: boolean) | | | TableScan [TS_74] | | | alias:y | | |<-Map 29 [CONTAINS] | | Reduce Output Operator [RS_89] | | key expressions:_col0 (type: string), _col1 (type: string) | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | sort order:++ | | Group By Operator [GBY_88] | | keys:_col0 (type: string), _col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Select Operator [SEL_84] | | outputColumnNames:["_col0","_col1"] | | Filter Operator [FIL_162] | | predicate:value is not null (type: boolean) | | TableScan [TS_83] | | alias:y | |<-Select Operator [SEL_71] | outputColumnNames:["_col0","_col1"] | Filter Operator [FIL_159] | predicate:key is not null (type: boolean) | TableScan [TS_70] | alias:y |<-Reducer 3 [CONTAINS] Reduce Output Operator [RS_119] key expressions:_col0 (type: string), _col1 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string) sort order:++ Group By Operator [GBY_118] keys:_col0 (type: string), _col1 (type: string) outputColumnNames:["_col0","_col1"] Group By Operator [GBY_68] | keys:KEY._col0 (type: string), KEY._col1 (type: string) | outputColumnNames:["_col0","_col1"] |<-Union 2 [SIMPLE_EDGE] |<-Map 11 [CONTAINS] | Reduce Output Operator [RS_67] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Group By Operator [GBY_66] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Select Operator [SEL_62] | outputColumnNames:["_col0","_col1"] | Map Join Operator [MAPJOIN_168] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"Map 11":"_col0 (type: string)","Reducer 16":"_col1 (type: string)"} | | outputColumnNames:["_col1","_col3"] | |<-Reducer 16 [BROADCAST_EDGE] | | Reduce Output Operator [RS_60] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ | | Statistics:Num rows: 209 Data size: 2208 Basic stats: COMPLETE Column stats: NONE | | Map Join Operator [MAPJOIN_167] | | | condition map:[{"":"Inner Join 0 to 1"}] | | | keys:{"Map 19":"_col1 (type: string)","Reducer 16":"_col0 (type: string)"} | | | outputColumnNames:["_col1"] | | | Statistics:Num rows: 209 Data size: 2208 Basic stats: COMPLETE Column stats: NONE | | |<-Map 19 [BROADCAST_EDGE] | | | Reduce Output Operator [RS_54] | | | key expressions:_col1 (type: string) | | | Map-reduce partition columns:_col1 (type: string) | | | sort order:+ | | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | | value expressions:_col0 (type: string) | | | Select Operator [SEL_50] | | | outputColumnNames:["_col0","_col1"] | | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | | Filter Operator [FIL_158] | | | predicate:(value is not null and key is not null) (type: boolean) | | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | | TableScan [TS_49] | | | alias:x | | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | | |<-Select Operator [SEL_48] | | outputColumnNames:["_col0"] | | Statistics:Num rows: 190 Data size: 2008 Basic stats: COMPLETE Column stats: NONE | | Group By Operator [GBY_47] | | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | | outputColumnNames:["_col0","_col1"] | | | Statistics:Num rows: 190 Data size: 2008 Basic stats: COMPLETE Column stats: NONE | | |<-Union 15 [SIMPLE_EDGE] | | |<-Reducer 14 [CONTAINS] | | | Reduce Output Operator [RS_46] | | | key expressions:_col0 (type: string), _col1 (type: string) | | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | | sort order:++ | | | Group By Operator [GBY_45] | | | keys:_col0 (type: string), _col1 (type: string) | | | outputColumnNames:["_col0","_col1"] | | | Group By Operator [GBY_38] | | | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | | | outputColumnNames:["_col0","_col1"] | | | |<-Union 13 [SIMPLE_EDGE] | | | |<-Map 12 [CONTAINS] | | | | Reduce Output Operator [RS_37] | | | | key expressions:_col0 (type: string), _col1 (type: string) | | | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | | | sort order:++ | | | | Group By Operator [GBY_36] | | | | keys:_col0 (type: string), _col1 (type: string) | | | | outputColumnNames:["_col0","_col1"] | | | | Select Operator [SEL_30] | | | | outputColumnNames:["_col0","_col1"] | | | | Filter Operator [FIL_155] | | | | predicate:value is not null (type: boolean) | | | | TableScan [TS_29] | | | | alias:x | | | |<-Map 17 [CONTAINS] | | | Reduce Output Operator [RS_37] | | | key expressions:_col0 (type: string), _col1 (type: string) | | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | | sort order:++ | | | Group By Operator [GBY_36] | | | keys:_col0 (type: string), _col1 (type: string) | | | outputColumnNames:["_col0","_col1"] | | | Select Operator [SEL_32] | | | outputColumnNames:["_col0","_col1"] | | | Filter Operator [FIL_156] | | | predicate:value is not null (type: boolean) | | | TableScan [TS_31] | | | alias:y | | |<-Map 18 [CONTAINS] | | Reduce Output Operator [RS_46] | | key expressions:_col0 (type: string), _col1 (type: string) | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | sort order:++ | | Group By Operator [GBY_45] | | keys:_col0 (type: string), _col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Select Operator [SEL_41] | | outputColumnNames:["_col0","_col1"] | | Filter Operator [FIL_157] | | predicate:value is not null (type: boolean) | | TableScan [TS_40] | | alias:y | |<-Select Operator [SEL_28] | outputColumnNames:["_col0","_col1"] | Filter Operator [FIL_154] | predicate:key is not null (type: boolean) | TableScan [TS_27] | alias:y |<-Map 1 [CONTAINS] Reduce Output Operator [RS_67] key expressions:_col0 (type: string), _col1 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string) sort order:++ Group By Operator [GBY_66] keys:_col0 (type: string), _col1 (type: string) outputColumnNames:["_col0","_col1"] Select Operator [SEL_26] outputColumnNames:["_col0","_col1"] Map Join Operator [MAPJOIN_166] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"Map 1":"_col0 (type: string)","Reducer 8":"_col1 (type: string)"} | outputColumnNames:["_col1","_col3"] |<-Reducer 8 [BROADCAST_EDGE] | Reduce Output Operator [RS_24] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ | Statistics:Num rows: 144 Data size: 1509 Basic stats: COMPLETE Column stats: NONE | Map Join Operator [MAPJOIN_165] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"Map 10":"_col1 (type: string)","Reducer 8":"_col0 (type: string)"} | | outputColumnNames:["_col1"] | | Statistics:Num rows: 144 Data size: 1509 Basic stats: COMPLETE Column stats: NONE | |<-Map 10 [BROADCAST_EDGE] | | Reduce Output Operator [RS_18] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col0 (type: string) | | Select Operator [SEL_14] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | Filter Operator [FIL_153] | | predicate:(value is not null and key is not null) (type: boolean) | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | TableScan [TS_13] | | alias:x | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | |<-Select Operator [SEL_12] | outputColumnNames:["_col0"] | Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE | Group By Operator [GBY_11] | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE | |<-Union 7 [SIMPLE_EDGE] | |<-Map 6 [CONTAINS] | | Reduce Output Operator [RS_10] | | key expressions:_col0 (type: string), _col1 (type: string) | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | sort order:++ | | Group By Operator [GBY_9] | | keys:_col0 (type: string), _col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Select Operator [SEL_3] | | outputColumnNames:["_col0","_col1"] | | Filter Operator [FIL_151] | | predicate:value is not null (type: boolean) | | TableScan [TS_2] | | alias:x | |<-Map 9 [CONTAINS] | Reduce Output Operator [RS_10] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Group By Operator [GBY_9] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Select Operator [SEL_5] | outputColumnNames:["_col0","_col1"] | Filter Operator [FIL_152] | predicate:value is not null (type: boolean) | TableScan [TS_4] | alias:y |<-Select Operator [SEL_1] outputColumnNames:["_col0","_col1"] Filter Operator [FIL_150] predicate:key is not null (type: boolean) TableScan [TS_0] alias:y PREHOOK: query: CREATE TABLE srcbucket_mapjoin(key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@srcbucket_mapjoin POSTHOOK: query: CREATE TABLE srcbucket_mapjoin(key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@srcbucket_mapjoin PREHOOK: query: CREATE TABLE tab_part (key int, value string) PARTITIONED BY(ds STRING) CLUSTERED BY (key) SORTED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@tab_part POSTHOOK: query: CREATE TABLE tab_part (key int, value string) PARTITIONED BY(ds STRING) CLUSTERED BY (key) SORTED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@tab_part PREHOOK: query: CREATE TABLE srcbucket_mapjoin_part (key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@srcbucket_mapjoin_part POSTHOOK: query: CREATE TABLE srcbucket_mapjoin_part (key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@srcbucket_mapjoin_part PREHOOK: query: load data local inpath '../../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin partition(ds='2008-04-08') PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@srcbucket_mapjoin POSTHOOK: query: load data local inpath '../../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin partition(ds='2008-04-08') POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@srcbucket_mapjoin POSTHOOK: Output: default@srcbucket_mapjoin@ds=2008-04-08 PREHOOK: query: load data local inpath '../../data/files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin partition(ds='2008-04-08') PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@srcbucket_mapjoin@ds=2008-04-08 POSTHOOK: query: load data local inpath '../../data/files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin partition(ds='2008-04-08') POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@srcbucket_mapjoin@ds=2008-04-08 PREHOOK: query: load data local inpath '../../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@srcbucket_mapjoin_part POSTHOOK: query: load data local inpath '../../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@srcbucket_mapjoin_part POSTHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08 PREHOOK: query: load data local inpath '../../data/files/srcbucket21.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08 POSTHOOK: query: load data local inpath '../../data/files/srcbucket21.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08 PREHOOK: query: load data local inpath '../../data/files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08 POSTHOOK: query: load data local inpath '../../data/files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08 PREHOOK: query: load data local inpath '../../data/files/srcbucket23.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08 POSTHOOK: query: load data local inpath '../../data/files/srcbucket23.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08 PREHOOK: query: insert overwrite table tab_part partition (ds='2008-04-08') select key,value from srcbucket_mapjoin_part PREHOOK: type: QUERY PREHOOK: Input: default@srcbucket_mapjoin_part PREHOOK: Input: default@srcbucket_mapjoin_part@ds=2008-04-08 PREHOOK: Output: default@tab_part@ds=2008-04-08 POSTHOOK: query: insert overwrite table tab_part partition (ds='2008-04-08') select key,value from srcbucket_mapjoin_part POSTHOOK: type: QUERY POSTHOOK: Input: default@srcbucket_mapjoin_part POSTHOOK: Input: default@srcbucket_mapjoin_part@ds=2008-04-08 POSTHOOK: Output: default@tab_part@ds=2008-04-08 POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin_part)srcbucket_mapjoin_part.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin_part)srcbucket_mapjoin_part.FieldSchema(name:value, type:string, comment:null), ] PREHOOK: query: CREATE TABLE tab(key int, value string) PARTITIONED BY(ds STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@tab POSTHOOK: query: CREATE TABLE tab(key int, value string) PARTITIONED BY(ds STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@tab PREHOOK: query: insert overwrite table tab partition (ds='2008-04-08') select key,value from srcbucket_mapjoin PREHOOK: type: QUERY PREHOOK: Input: default@srcbucket_mapjoin PREHOOK: Input: default@srcbucket_mapjoin@ds=2008-04-08 PREHOOK: Output: default@tab@ds=2008-04-08 POSTHOOK: query: insert overwrite table tab partition (ds='2008-04-08') select key,value from srcbucket_mapjoin POSTHOOK: type: QUERY POSTHOOK: Input: default@srcbucket_mapjoin POSTHOOK: Input: default@srcbucket_mapjoin@ds=2008-04-08 POSTHOOK: Output: default@tab@ds=2008-04-08 POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:value, type:string, comment:null), ] PREHOOK: query: CREATE TABLE tab2(key int, value string) PARTITIONED BY(ds STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@tab2 POSTHOOK: query: CREATE TABLE tab2(key int, value string) PARTITIONED BY(ds STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@tab2 PREHOOK: query: insert overwrite table tab2 partition (ds='2008-04-08') select key,value from srcbucket_mapjoin PREHOOK: type: QUERY PREHOOK: Input: default@srcbucket_mapjoin PREHOOK: Input: default@srcbucket_mapjoin@ds=2008-04-08 PREHOOK: Output: default@tab2@ds=2008-04-08 POSTHOOK: query: insert overwrite table tab2 partition (ds='2008-04-08') select key,value from srcbucket_mapjoin POSTHOOK: type: QUERY POSTHOOK: Input: default@srcbucket_mapjoin POSTHOOK: Input: default@srcbucket_mapjoin@ds=2008-04-08 POSTHOOK: Output: default@tab2@ds=2008-04-08 POSTHOOK: Lineage: tab2 PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: tab2 PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:value, type:string, comment:null), ] PREHOOK: query: explain select s1.key as key, s1.value as value from tab s1 join tab s3 on s1.key=s3.key PREHOOK: type: QUERY POSTHOOK: query: explain select s1.key as key, s1.value as value from tab s1 join tab s3 on s1.key=s3.key POSTHOOK: type: QUERY Plan not optimized by CBO due to missing statistics. Please check log for more details. Stage-0 Fetch Operator limit:-1 Stage-1 Map 1 File Output Operator [FS_8] compressed:false Statistics:Num rows: 133 Data size: 1411 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_13] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"1":"key (type: int)","0":"key (type: int)"} | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE | |<-Filter Operator [FIL_12] | predicate:key is not null (type: boolean) | Statistics:Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_1] | alias:s3 | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE |<-Filter Operator [FIL_11] predicate:key is not null (type: boolean) Statistics:Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE TableScan [TS_0] alias:s1 Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: explain select s1.key as key, s1.value as value from tab s1 join tab s3 on s1.key=s3.key join tab s2 on s1.value=s2.value PREHOOK: type: QUERY POSTHOOK: query: explain select s1.key as key, s1.value as value from tab s1 join tab s3 on s1.key=s3.key join tab s2 on s1.value=s2.value 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), Map 4 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_14] compressed:false Statistics:Num rows: 146 Data size: 1552 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_25] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"1":"value (type: string)","0":"_col1 (type: string)"} | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 146 Data size: 1552 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_9] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ | Statistics:Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE | value expressions:_col0 (type: int) | Merge Join Operator [MERGEJOIN_23] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"1":"key (type: int)","0":"key (type: int)"} | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE | | | |<-Filter Operator [FIL_21] | | predicate:key is not null (type: boolean) | | Statistics:Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE | | TableScan [TS_1] | | alias:s3 | | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE | |<-Filter Operator [FIL_20] | predicate:(key is not null and value is not null) (type: boolean) | Statistics:Num rows: 61 Data size: 646 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_0] | alias:s1 | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE |<-Map 4 [SIMPLE_EDGE] Reduce Output Operator [RS_11] key expressions:value (type: string) Map-reduce partition columns:value (type: string) sort order:+ Statistics:Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE Filter Operator [FIL_22] predicate:value is not null (type: boolean) Statistics:Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE TableScan [TS_2] alias:s2 Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: explain select s1.key as key, s1.value as value from tab s1 join tab2 s3 on s1.key=s3.key PREHOOK: type: QUERY POSTHOOK: query: explain select s1.key as key, s1.value as value from tab s1 join tab2 s3 on s1.key=s3.key POSTHOOK: type: QUERY Plan not optimized by CBO due to missing statistics. Please check log for more details. Stage-0 Fetch Operator limit:-1 Stage-1 Map 1 File Output Operator [FS_8] compressed:false Statistics:Num rows: 133 Data size: 1411 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_13] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"1":"key (type: int)","0":"key (type: int)"} | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE | |<-Filter Operator [FIL_12] | predicate:key is not null (type: boolean) | Statistics:Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_1] | alias:s3 | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE |<-Filter Operator [FIL_11] predicate:key is not null (type: boolean) Statistics:Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE TableScan [TS_0] alias:s1 Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: explain select s1.key as key, s1.value as value from tab s1 join tab2 s3 on s1.key=s3.key join tab2 s2 on s1.value=s2.value PREHOOK: type: QUERY POSTHOOK: query: explain select s1.key as key, s1.value as value from tab s1 join tab2 s3 on s1.key=s3.key join tab2 s2 on s1.value=s2.value 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), Map 4 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 2 File Output Operator [FS_14] compressed:false Statistics:Num rows: 146 Data size: 1552 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_25] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"1":"value (type: string)","0":"_col1 (type: string)"} | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 146 Data size: 1552 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_9] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ | Statistics:Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE | value expressions:_col0 (type: int) | Merge Join Operator [MERGEJOIN_23] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"1":"key (type: int)","0":"key (type: int)"} | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE | | | |<-Filter Operator [FIL_21] | | predicate:key is not null (type: boolean) | | Statistics:Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE | | TableScan [TS_1] | | alias:s3 | | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE | |<-Filter Operator [FIL_20] | predicate:(key is not null and value is not null) (type: boolean) | Statistics:Num rows: 61 Data size: 646 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_0] | alias:s1 | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE |<-Map 4 [SIMPLE_EDGE] Reduce Output Operator [RS_11] key expressions:value (type: string) Map-reduce partition columns:value (type: string) sort order:+ Statistics:Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE Filter Operator [FIL_22] predicate:value is not null (type: boolean) Statistics:Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE TableScan [TS_2] alias:s2 Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: explain select count(*) from (select s1.key as key, s1.value as value from tab s1 join tab s3 on s1.key=s3.key UNION ALL select s2.key as key, s2.value as value from tab s2 ) a join tab_part b on (a.key = b.key) PREHOOK: type: QUERY POSTHOOK: query: explain select count(*) from (select s1.key as key, s1.value as value from tab s1 join tab s3 on s1.key=s3.key UNION ALL select s2.key as key, s2.value as value from tab s2 ) a join tab_part 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 3 <- Map 7 (SIMPLE_EDGE), Union 2 (SIMPLE_EDGE) Map 1 <- Union 2 (CONTAINS) Reducer 4 <- Reducer 3 (SIMPLE_EDGE) Map 6 <- Union 2 (CONTAINS) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 4 File Output Operator [FS_22] 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_20] | aggregations:["count(VALUE._col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE |<-Reducer 3 [SIMPLE_EDGE] Reduce Output Operator [RS_19] sort order: Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions:_col0 (type: bigint) Group By Operator [GBY_18] aggregations:["count()"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Merge Join Operator [MERGEJOIN_35] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"1":"key (type: int)","0":"_col0 (type: int)"} | Statistics:Num rows: 279 Data size: 2963 Basic stats: COMPLETE Column stats: NONE |<-Map 7 [SIMPLE_EDGE] | Reduce Output Operator [RS_15] | key expressions:key (type: int) | Map-reduce partition columns:key (type: int) | sort order:+ | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | Filter Operator [FIL_32] | predicate:key is not null (type: boolean) | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_11] | alias:b | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE |<-Union 2 [SIMPLE_EDGE] |<-Map 1 [CONTAINS] | Reduce Output Operator [RS_13] | key expressions:_col0 (type: int) | Map-reduce partition columns:_col0 (type: int) | sort order:+ | Merge Join Operator [MERGEJOIN_33] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"1":"key (type: int)","0":"key (type: int)"} | | outputColumnNames:["_col0"] | | | |<-Filter Operator [FIL_30] | | predicate:key is not null (type: boolean) | | Statistics:Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE | | TableScan [TS_1] | | alias:s3 | | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE | |<-Filter Operator [FIL_29] | predicate:key is not null (type: boolean) | TableScan [TS_0] | alias:s1 |<-Map 6 [CONTAINS] Reduce Output Operator [RS_13] key expressions:_col0 (type: int) Map-reduce partition columns:_col0 (type: int) sort order:+ Select Operator [SEL_9] outputColumnNames:["_col0"] Filter Operator [FIL_31] predicate:key is not null (type: boolean) TableScan [TS_8] alias:s2 PREHOOK: query: explain select count(*) from (select s1.key as key, s1.value as value from tab s1 join tab s3 on s1.key=s3.key join tab s2 on s1.value=s2.value UNION ALL select s2.key as key, s2.value as value from tab s2 ) a join tab_part b on (a.key = b.key) PREHOOK: type: QUERY POSTHOOK: query: explain select count(*) from (select s1.key as key, s1.value as value from tab s1 join tab s3 on s1.key=s3.key join tab s2 on s1.value=s2.value UNION ALL select s2.key as key, s2.value as value from tab s2 ) a join tab_part 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), Map 7 (SIMPLE_EDGE), Union 3 (CONTAINS) Reducer 5 <- Reducer 4 (SIMPLE_EDGE) Reducer 4 <- Map 9 (SIMPLE_EDGE), Union 3 (SIMPLE_EDGE) Map 8 <- Union 3 (CONTAINS) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 5 File Output Operator [FS_28] 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_26] | aggregations:["count(VALUE._col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE |<-Reducer 4 [SIMPLE_EDGE] Reduce Output Operator [RS_25] sort order: Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions:_col0 (type: bigint) Group By Operator [GBY_24] aggregations:["count()"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Merge Join Operator [MERGEJOIN_47] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"1":"key (type: int)","0":"_col0 (type: int)"} | Statistics:Num rows: 293 Data size: 3118 Basic stats: COMPLETE Column stats: NONE |<-Map 9 [SIMPLE_EDGE] | Reduce Output Operator [RS_21] | key expressions:key (type: int) | Map-reduce partition columns:key (type: int) | sort order:+ | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | Filter Operator [FIL_43] | predicate:key is not null (type: boolean) | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_17] | alias:b | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE |<-Union 3 [SIMPLE_EDGE] |<-Reducer 2 [CONTAINS] | Reduce Output Operator [RS_19] | key expressions:_col0 (type: int) | Map-reduce partition columns:_col0 (type: int) | sort order:+ | Merge Join Operator [MERGEJOIN_46] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"1":"value (type: string)","0":"_col1 (type: string)"} | | outputColumnNames:["_col0"] | |<-Map 1 [SIMPLE_EDGE] | | Reduce Output Operator [RS_9] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ | | Statistics:Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col0 (type: int) | | Merge Join Operator [MERGEJOIN_44] | | | condition map:[{"":"Inner Join 0 to 1"}] | | | keys:{"1":"key (type: int)","0":"key (type: int)"} | | | outputColumnNames:["_col0","_col1"] | | | Statistics:Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE | | | | | |<-Filter Operator [FIL_40] | | | predicate:key is not null (type: boolean) | | | Statistics:Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE | | | TableScan [TS_1] | | | alias:s3 | | | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE | | |<-Filter Operator [FIL_39] | | predicate:(key is not null and value is not null) (type: boolean) | | Statistics:Num rows: 61 Data size: 646 Basic stats: COMPLETE Column stats: NONE | | TableScan [TS_0] | | alias:s1 | | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE | |<-Map 7 [SIMPLE_EDGE] | Reduce Output Operator [RS_11] | key expressions:value (type: string) | Map-reduce partition columns:value (type: string) | sort order:+ | Statistics:Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE | Filter Operator [FIL_41] | predicate:value is not null (type: boolean) | Statistics:Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_2] | alias:s2 | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE |<-Map 8 [CONTAINS] Reduce Output Operator [RS_19] key expressions:_col0 (type: int) Map-reduce partition columns:_col0 (type: int) sort order:+ Select Operator [SEL_15] outputColumnNames:["_col0"] Filter Operator [FIL_42] predicate:key is not null (type: boolean) TableScan [TS_14] alias:s2 PREHOOK: query: explain SELECT x.key, y.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN (select * from src1 union all select * from src)z ON (x.value = z.value) union all SELECT x.key, y.value FROM src x JOIN src y ON (x.key = y.key) JOIN (select key, value from src1 union all select key, value from src union all select key, value from src)z ON (x.value = z.value) union all SELECT x.key, y.value FROM src1 x JOIN src1 y ON (x.key = y.key) JOIN (select key, value from src1 union all select key, value from src union all select key, value from src union all select key, value from src)z ON (x.value = z.value) PREHOOK: type: QUERY POSTHOOK: query: explain SELECT x.key, y.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN (select * from src1 union all select * from src)z ON (x.value = z.value) union all SELECT x.key, y.value FROM src x JOIN src y ON (x.key = y.key) JOIN (select key, value from src1 union all select key, value from src union all select key, value from src)z ON (x.value = z.value) union all SELECT x.key, y.value FROM src1 x JOIN src1 y ON (x.key = y.key) JOIN (select key, value from src1 union all select key, value from src union all select key, value from src union all select key, value from src)z ON (x.value = z.value) POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Reducer 2 <- Map 1 (SIMPLE_EDGE), Union 3 (CONTAINS), Union 5 (SIMPLE_EDGE) Map 12 <- Union 9 (CONTAINS) Reducer 11 <- Map 15 (SIMPLE_EDGE), Reducer 10 (SIMPLE_EDGE), Union 3 (CONTAINS) Map 13 <- Union 9 (CONTAINS) Reducer 10 <- Map 14 (SIMPLE_EDGE), Union 9 (SIMPLE_EDGE) Map 4 <- Map 7 (BROADCAST_EDGE), Union 5 (CONTAINS) Map 19 <- Map 20 (BROADCAST_EDGE), Map 21 (BROADCAST_EDGE), Union 3 (CONTAINS) Map 6 <- Map 7 (BROADCAST_EDGE), Union 5 (CONTAINS) Map 16 <- Map 20 (BROADCAST_EDGE), Map 21 (BROADCAST_EDGE), Union 3 (CONTAINS) Map 8 <- Union 9 (CONTAINS) Map 18 <- Map 20 (BROADCAST_EDGE), Map 21 (BROADCAST_EDGE), Union 3 (CONTAINS) Map 17 <- Map 20 (BROADCAST_EDGE), Map 21 (BROADCAST_EDGE), Union 3 (CONTAINS) Stage-0 Fetch Operator limit:-1 Stage-1 Union 3 |<-Reducer 2 [CONTAINS] | File Output Operator [FS_76] | compressed:false | 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_21] | outputColumnNames:["_col0","_col1"] | Merge Join Operator [MERGEJOIN_120] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"1":"_col1 (type: string)","0":"_col0 (type: string)"} | | outputColumnNames:["_col1","_col3"] | |<-Map 1 [SIMPLE_EDGE] | | Reduce Output Operator [RS_17] | | key expressions:_col0 (type: string) | | Map-reduce partition columns:_col0 (type: string) | | sort order:+ | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col1 (type: string) | | Select Operator [SEL_1] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | | Filter Operator [FIL_104] | | predicate:key is not null (type: boolean) | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | | TableScan [TS_0] | | alias:y | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | |<-Union 5 [SIMPLE_EDGE] | |<-Map 4 [CONTAINS] | | Reduce Output Operator [RS_19] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ | | Map Join Operator [MAPJOIN_119] | | | condition map:[{"":"Inner Join 0 to 1"}] | | | keys:{"Map 4":"_col0 (type: string)","Map 7":"_col1 (type: string)"} | | | outputColumnNames:["_col1"] | | |<-Map 7 [BROADCAST_EDGE] | | | Reduce Output Operator [RS_13] | | | key expressions:_col1 (type: string) | | | Map-reduce partition columns:_col1 (type: string) | | | sort order:+ | | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | | value expressions:_col0 (type: string) | | | Select Operator [SEL_9] | | | outputColumnNames:["_col0","_col1"] | | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | | Filter Operator [FIL_107] | | | predicate:(value is not null and key is not null) (type: boolean) | | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | | TableScan [TS_8] | | | alias:x | | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | | | Reduce Output Operator [RS_125] | | | key expressions:_col1 (type: string) | | | Map-reduce partition columns:_col1 (type: string) | | | sort order:+ | | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | | value expressions:_col0 (type: string) | | | Please refer to the previous Select Operator [SEL_9] | | |<-Select Operator [SEL_3] | | outputColumnNames:["_col0"] | | Filter Operator [FIL_105] | | predicate:value is not null (type: boolean) | | TableScan [TS_2] | | alias:x | |<-Map 6 [CONTAINS] | Reduce Output Operator [RS_19] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ | Map Join Operator [MAPJOIN_119] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"Map 7":"_col1 (type: string)","Map 6":"_col0 (type: string)"} | | outputColumnNames:["_col1"] | |<- Please refer to the previous Map 7 [BROADCAST_EDGE] | |<-Select Operator [SEL_5] | outputColumnNames:["_col0"] | Filter Operator [FIL_106] | predicate:value is not null (type: boolean) | TableScan [TS_4] | alias:y |<-Reducer 11 [CONTAINS] | File Output Operator [FS_76] | compressed:false | 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_45] | outputColumnNames:["_col0","_col1"] | Merge Join Operator [MERGEJOIN_122] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"1":"_col0 (type: string)","0":"_col1 (type: string)"} | | outputColumnNames:["_col1","_col4"] | |<-Map 15 [SIMPLE_EDGE] | | Reduce Output Operator [RS_43] | | key expressions:_col0 (type: string) | | Map-reduce partition columns:_col0 (type: string) | | sort order:+ | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col1 (type: string) | | Select Operator [SEL_34] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | | Filter Operator [FIL_112] | | predicate:key is not null (type: boolean) | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | | TableScan [TS_33] | | alias:y | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | |<-Reducer 10 [SIMPLE_EDGE] | Reduce Output Operator [RS_41] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ | Statistics:Num rows: 564 Data size: 5952 Basic stats: COMPLETE Column stats: NONE | Merge Join Operator [MERGEJOIN_121] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"1":"_col1 (type: string)","0":"_col0 (type: string)"} | | outputColumnNames:["_col1"] | | Statistics:Num rows: 564 Data size: 5952 Basic stats: COMPLETE Column stats: NONE | |<-Map 14 [SIMPLE_EDGE] | | Reduce Output Operator [RS_38] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ | | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col0 (type: string) | | Select Operator [SEL_32] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE | | Filter Operator [FIL_111] | | predicate:(value is not null and key is not null) (type: boolean) | | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE | | TableScan [TS_31] | | alias:y | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | |<-Union 9 [SIMPLE_EDGE] | |<-Map 12 [CONTAINS] | | Reduce Output Operator [RS_36] | | key expressions:_col0 (type: string) | | Map-reduce partition columns:_col0 (type: string) | | sort order:+ | | Select Operator [SEL_25] | | outputColumnNames:["_col0"] | | Filter Operator [FIL_109] | | predicate:value is not null (type: boolean) | | TableScan [TS_24] | | alias:y | |<-Map 13 [CONTAINS] | | Reduce Output Operator [RS_36] | | key expressions:_col0 (type: string) | | Map-reduce partition columns:_col0 (type: string) | | sort order:+ | | Select Operator [SEL_29] | | outputColumnNames:["_col0"] | | Filter Operator [FIL_110] | | predicate:value is not null (type: boolean) | | TableScan [TS_28] | | alias:y | |<-Map 8 [CONTAINS] | Reduce Output Operator [RS_36] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Select Operator [SEL_23] | outputColumnNames:["_col0"] | Filter Operator [FIL_108] | predicate:value is not null (type: boolean) | TableScan [TS_22] | alias:x |<-Map 19 [CONTAINS] | File Output Operator [FS_76] | compressed:false | 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_74] | outputColumnNames:["_col0","_col1"] | Map Join Operator [MAPJOIN_124] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"Map 21":"_col0 (type: string)","Map 19":"_col1 (type: string)"} | | outputColumnNames:["_col1","_col4"] | |<-Map 21 [BROADCAST_EDGE] | | Reduce Output Operator [RS_72] | | key expressions:_col0 (type: string) | | Map-reduce partition columns:_col0 (type: string) | | sort order:+ | | Statistics:Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col1 (type: string) | | Select Operator [SEL_63] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE | | Filter Operator [FIL_118] | | predicate:key is not null (type: boolean) | | Statistics:Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE | | TableScan [TS_62] | | alias:x | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | | Reduce Output Operator [RS_131] | | key expressions:_col0 (type: string) | | Map-reduce partition columns:_col0 (type: string) | | sort order:+ | | Statistics:Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col1 (type: string) | | Please refer to the previous Select Operator [SEL_63] | | Reduce Output Operator [RS_132] | | key expressions:_col0 (type: string) | | Map-reduce partition columns:_col0 (type: string) | | sort order:+ | | Statistics:Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col1 (type: string) | | Please refer to the previous Select Operator [SEL_63] | | Reduce Output Operator [RS_133] | | key expressions:_col0 (type: string) | | Map-reduce partition columns:_col0 (type: string) | | sort order:+ | | Statistics:Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col1 (type: string) | | Please refer to the previous Select Operator [SEL_63] | |<-Map Join Operator [MAPJOIN_123] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"Map 20":"_col1 (type: string)","Map 19":"_col0 (type: string)"} | | outputColumnNames:["_col1"] | |<-Map 20 [BROADCAST_EDGE] | | Reduce Output Operator [RS_67] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col0 (type: string) | | Select Operator [SEL_61] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | Filter Operator [FIL_117] | | predicate:(value is not null and key is not null) (type: boolean) | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | TableScan [TS_60] | | alias:x | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | | Reduce Output Operator [RS_127] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col0 (type: string) | | Please refer to the previous Select Operator [SEL_61] | | Reduce Output Operator [RS_128] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col0 (type: string) | | Please refer to the previous Select Operator [SEL_61] | | Reduce Output Operator [RS_129] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col0 (type: string) | | Please refer to the previous Select Operator [SEL_61] | |<-Select Operator [SEL_58] | outputColumnNames:["_col0"] | Filter Operator [FIL_116] | predicate:value is not null (type: boolean) | TableScan [TS_57] | alias:y |<-Map 16 [CONTAINS] | File Output Operator [FS_76] | compressed:false | 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_74] | outputColumnNames:["_col0","_col1"] | Map Join Operator [MAPJOIN_124] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"Map 21":"_col0 (type: string)","Map 16":"_col1 (type: string)"} | | outputColumnNames:["_col1","_col4"] | |<- Please refer to the previous Map 21 [BROADCAST_EDGE] | |<-Map Join Operator [MAPJOIN_123] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"Map 20":"_col1 (type: string)","Map 16":"_col0 (type: string)"} | | outputColumnNames:["_col1"] | |<- Please refer to the previous Map 20 [BROADCAST_EDGE] | |<-Select Operator [SEL_49] | outputColumnNames:["_col0"] | Filter Operator [FIL_113] | predicate:value is not null (type: boolean) | TableScan [TS_48] | alias:x |<-Map 18 [CONTAINS] | File Output Operator [FS_76] | compressed:false | 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_74] | outputColumnNames:["_col0","_col1"] | Map Join Operator [MAPJOIN_124] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"Map 21":"_col0 (type: string)","Map 18":"_col1 (type: string)"} | | outputColumnNames:["_col1","_col4"] | |<- Please refer to the previous Map 21 [BROADCAST_EDGE] | |<-Map Join Operator [MAPJOIN_123] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"Map 20":"_col1 (type: string)","Map 18":"_col0 (type: string)"} | | outputColumnNames:["_col1"] | |<- Please refer to the previous Map 20 [BROADCAST_EDGE] | |<-Select Operator [SEL_55] | outputColumnNames:["_col0"] | Filter Operator [FIL_115] | predicate:value is not null (type: boolean) | TableScan [TS_54] | alias:y |<-Map 17 [CONTAINS] File Output Operator [FS_76] compressed:false 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_74] outputColumnNames:["_col0","_col1"] Map Join Operator [MAPJOIN_124] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"Map 21":"_col0 (type: string)","Map 17":"_col1 (type: string)"} | outputColumnNames:["_col1","_col4"] |<- Please refer to the previous Map 21 [BROADCAST_EDGE] |<-Map Join Operator [MAPJOIN_123] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"Map 20":"_col1 (type: string)","Map 17":"_col0 (type: string)"} | outputColumnNames:["_col1"] |<- Please refer to the previous Map 20 [BROADCAST_EDGE] |<-Select Operator [SEL_51] outputColumnNames:["_col0"] Filter Operator [FIL_114] predicate:value is not null (type: boolean) TableScan [TS_50] alias:y PREHOOK: query: explain SELECT x.key, y.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN (select * from src1 union select * from src)z ON (x.value = z.value) union SELECT x.key, y.value FROM src x JOIN src y ON (x.key = y.key) JOIN (select key, value from src1 union select key, value from src union select key, value from src)z ON (x.value = z.value) union SELECT x.key, y.value FROM src1 x JOIN src1 y ON (x.key = y.key) JOIN (select key, value from src1 union select key, value from src union select key, value from src union select key, value from src)z ON (x.value = z.value) PREHOOK: type: QUERY POSTHOOK: query: explain SELECT x.key, y.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN (select * from src1 union select * from src)z ON (x.value = z.value) union SELECT x.key, y.value FROM src x JOIN src y ON (x.key = y.key) JOIN (select key, value from src1 union select key, value from src union select key, value from src)z ON (x.value = z.value) union SELECT x.key, y.value FROM src1 x JOIN src1 y ON (x.key = y.key) JOIN (select key, value from src1 union select key, value from src union select key, value from src union select key, value from src)z ON (x.value = z.value) POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage Map 12 <- Union 13 (CONTAINS) Map 30 <- Union 24 (CONTAINS) Reducer 14 <- Union 13 (SIMPLE_EDGE), Union 15 (CONTAINS) Map 23 <- Union 24 (CONTAINS) Map 32 <- Union 28 (CONTAINS) Reducer 25 <- Union 24 (SIMPLE_EDGE), Union 26 (CONTAINS) Map 31 <- Union 26 (CONTAINS) Map 20 <- Union 15 (CONTAINS) Map 10 <- Union 8 (CONTAINS) Reducer 4 <- Union 3 (SIMPLE_EDGE), Union 5 (CONTAINS) Map 19 <- Union 13 (CONTAINS) Reducer 6 <- Union 5 (SIMPLE_EDGE) Reducer 9 <- Map 11 (BROADCAST_EDGE), Union 8 (SIMPLE_EDGE) Reducer 17 <- Map 21 (SIMPLE_EDGE), Reducer 16 (SIMPLE_EDGE) Reducer 27 <- Union 26 (SIMPLE_EDGE), Union 28 (CONTAINS) Reducer 18 <- Map 22 (SIMPLE_EDGE), Reducer 17 (SIMPLE_EDGE), Union 3 (CONTAINS) Reducer 29 <- Map 33 (BROADCAST_EDGE), Map 34 (BROADCAST_EDGE), Union 28 (SIMPLE_EDGE), Union 5 (CONTAINS) Reducer 16 <- Union 15 (SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE), Union 3 (CONTAINS) Map 7 <- Union 8 (CONTAINS) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 6 File Output Operator [FS_120] compressed:false Statistics:Num rows: 270 Data size: 2865 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_118] | keys:KEY._col0 (type: string), KEY._col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 270 Data size: 2865 Basic stats: COMPLETE Column stats: NONE |<-Union 5 [SIMPLE_EDGE] |<-Reducer 4 [CONTAINS] | Reduce Output Operator [RS_117] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Group By Operator [GBY_116] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Group By Operator [GBY_67] | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | outputColumnNames:["_col0","_col1"] | |<-Union 3 [SIMPLE_EDGE] | |<-Reducer 18 [CONTAINS] | | Reduce Output Operator [RS_66] | | key expressions:_col0 (type: string), _col1 (type: string) | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | sort order:++ | | Group By Operator [GBY_65] | | keys:_col0 (type: string), _col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Select Operator [SEL_61] | | outputColumnNames:["_col0","_col1"] | | Merge Join Operator [MERGEJOIN_166] | | | condition map:[{"":"Inner Join 0 to 1"}] | | | keys:{"1":"_col0 (type: string)","0":"_col1 (type: string)"} | | | outputColumnNames:["_col1","_col4"] | | |<-Map 22 [SIMPLE_EDGE] | | | Reduce Output Operator [RS_59] | | | key expressions:_col0 (type: string) | | | Map-reduce partition columns:_col0 (type: string) | | | sort order:+ | | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | | | value expressions:_col1 (type: string) | | | Select Operator [SEL_50] | | | outputColumnNames:["_col0","_col1"] | | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | | | Filter Operator [FIL_156] | | | predicate:key is not null (type: boolean) | | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | | | TableScan [TS_49] | | | alias:y | | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | | |<-Reducer 17 [SIMPLE_EDGE] | | Reduce Output Operator [RS_57] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ | | Statistics:Num rows: 209 Data size: 2208 Basic stats: COMPLETE Column stats: NONE | | Merge Join Operator [MERGEJOIN_165] | | | condition map:[{"":"Inner Join 0 to 1"}] | | | keys:{"1":"_col1 (type: string)","0":"_col0 (type: string)"} | | | outputColumnNames:["_col1"] | | | Statistics:Num rows: 209 Data size: 2208 Basic stats: COMPLETE Column stats: NONE | | |<-Map 21 [SIMPLE_EDGE] | | | Reduce Output Operator [RS_54] | | | key expressions:_col1 (type: string) | | | Map-reduce partition columns:_col1 (type: string) | | | sort order:+ | | | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE | | | value expressions:_col0 (type: string) | | | Select Operator [SEL_48] | | | outputColumnNames:["_col0","_col1"] | | | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE | | | Filter Operator [FIL_155] | | | predicate:(value is not null and key is not null) (type: boolean) | | | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE | | | TableScan [TS_47] | | | alias:y | | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | | |<-Reducer 16 [SIMPLE_EDGE] | | Reduce Output Operator [RS_52] | | key expressions:_col0 (type: string) | | Map-reduce partition columns:_col0 (type: string) | | sort order:+ | | Statistics:Num rows: 190 Data size: 2008 Basic stats: COMPLETE Column stats: NONE | | Select Operator [SEL_46] | | outputColumnNames:["_col0"] | | Statistics:Num rows: 190 Data size: 2008 Basic stats: COMPLETE Column stats: NONE | | Group By Operator [GBY_45] | | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | | outputColumnNames:["_col0","_col1"] | | | Statistics:Num rows: 190 Data size: 2008 Basic stats: COMPLETE Column stats: NONE | | |<-Union 15 [SIMPLE_EDGE] | | |<-Reducer 14 [CONTAINS] | | | Reduce Output Operator [RS_44] | | | key expressions:_col0 (type: string), _col1 (type: string) | | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | | sort order:++ | | | Group By Operator [GBY_43] | | | keys:_col0 (type: string), _col1 (type: string) | | | outputColumnNames:["_col0","_col1"] | | | Group By Operator [GBY_36] | | | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | | | outputColumnNames:["_col0","_col1"] | | | |<-Union 13 [SIMPLE_EDGE] | | | |<-Map 12 [CONTAINS] | | | | Reduce Output Operator [RS_35] | | | | key expressions:_col0 (type: string), _col1 (type: string) | | | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | | | sort order:++ | | | | Group By Operator [GBY_34] | | | | keys:_col0 (type: string), _col1 (type: string) | | | | outputColumnNames:["_col0","_col1"] | | | | Select Operator [SEL_28] | | | | outputColumnNames:["_col0","_col1"] | | | | Filter Operator [FIL_152] | | | | predicate:value is not null (type: boolean) | | | | TableScan [TS_27] | | | | alias:x | | | |<-Map 19 [CONTAINS] | | | Reduce Output Operator [RS_35] | | | key expressions:_col0 (type: string), _col1 (type: string) | | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | | sort order:++ | | | Group By Operator [GBY_34] | | | keys:_col0 (type: string), _col1 (type: string) | | | outputColumnNames:["_col0","_col1"] | | | Select Operator [SEL_30] | | | outputColumnNames:["_col0","_col1"] | | | Filter Operator [FIL_153] | | | predicate:value is not null (type: boolean) | | | TableScan [TS_29] | | | alias:y | | |<-Map 20 [CONTAINS] | | Reduce Output Operator [RS_44] | | key expressions:_col0 (type: string), _col1 (type: string) | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | sort order:++ | | Group By Operator [GBY_43] | | keys:_col0 (type: string), _col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Select Operator [SEL_39] | | outputColumnNames:["_col0","_col1"] | | Filter Operator [FIL_154] | | predicate:value is not null (type: boolean) | | TableScan [TS_38] | | alias:y | |<-Reducer 2 [CONTAINS] | Reduce Output Operator [RS_66] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Group By Operator [GBY_65] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Select Operator [SEL_26] | outputColumnNames:["_col0","_col1"] | Merge Join Operator [MERGEJOIN_164] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"1":"_col1 (type: string)","0":"_col0 (type: string)"} | | outputColumnNames:["_col1","_col3"] | |<-Map 1 [SIMPLE_EDGE] | | Reduce Output Operator [RS_22] | | key expressions:_col0 (type: string) | | Map-reduce partition columns:_col0 (type: string) | | sort order:+ | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col1 (type: string) | | Select Operator [SEL_1] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | | Filter Operator [FIL_148] | | predicate:key is not null (type: boolean) | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | | TableScan [TS_0] | | alias:y | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | |<-Reducer 9 [SIMPLE_EDGE] | Reduce Output Operator [RS_24] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ | Statistics:Num rows: 144 Data size: 1509 Basic stats: COMPLETE Column stats: NONE | Map Join Operator [MAPJOIN_163] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"Map 11":"_col1 (type: string)","Reducer 9":"_col0 (type: string)"} | | outputColumnNames:["_col1"] | | Statistics:Num rows: 144 Data size: 1509 Basic stats: COMPLETE Column stats: NONE | |<-Map 11 [BROADCAST_EDGE] | | Reduce Output Operator [RS_18] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col0 (type: string) | | Select Operator [SEL_14] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | Filter Operator [FIL_151] | | predicate:(value is not null and key is not null) (type: boolean) | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | TableScan [TS_13] | | alias:x | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | |<-Select Operator [SEL_12] | outputColumnNames:["_col0"] | Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE | Group By Operator [GBY_11] | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE | |<-Union 8 [SIMPLE_EDGE] | |<-Map 10 [CONTAINS] | | Reduce Output Operator [RS_10] | | key expressions:_col0 (type: string), _col1 (type: string) | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | sort order:++ | | Group By Operator [GBY_9] | | keys:_col0 (type: string), _col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Select Operator [SEL_5] | | outputColumnNames:["_col0","_col1"] | | Filter Operator [FIL_150] | | predicate:value is not null (type: boolean) | | TableScan [TS_4] | | alias:y | |<-Map 7 [CONTAINS] | Reduce Output Operator [RS_10] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Group By Operator [GBY_9] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Select Operator [SEL_3] | outputColumnNames:["_col0","_col1"] | Filter Operator [FIL_149] | predicate:value is not null (type: boolean) | TableScan [TS_2] | alias:x |<-Reducer 29 [CONTAINS] Reduce Output Operator [RS_117] key expressions:_col0 (type: string), _col1 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string) sort order:++ Group By Operator [GBY_116] keys:_col0 (type: string), _col1 (type: string) outputColumnNames:["_col0","_col1"] Select Operator [SEL_112] outputColumnNames:["_col0","_col1"] Map Join Operator [MAPJOIN_168] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"Map 34":"_col0 (type: string)","Reducer 29":"_col1 (type: string)"} | outputColumnNames:["_col1","_col4"] |<-Map 34 [BROADCAST_EDGE] | Reduce Output Operator [RS_110] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE | value expressions:_col1 (type: string) | Select Operator [SEL_101] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE | Filter Operator [FIL_162] | predicate:key is not null (type: boolean) | Statistics:Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_100] | alias:x | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE |<-Map Join Operator [MAPJOIN_167] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"Map 33":"_col1 (type: string)","Reducer 29":"_col0 (type: string)"} | outputColumnNames:["_col1"] |<-Map 33 [BROADCAST_EDGE] | Reduce Output Operator [RS_105] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | value expressions:_col0 (type: string) | Select Operator [SEL_99] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | Filter Operator [FIL_161] | predicate:(value is not null and key is not null) (type: boolean) | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_98] | alias:x | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE |<-Select Operator [SEL_97] outputColumnNames:["_col0"] Group By Operator [GBY_96] | keys:KEY._col0 (type: string), KEY._col1 (type: string) | outputColumnNames:["_col0","_col1"] |<-Union 28 [SIMPLE_EDGE] |<-Map 32 [CONTAINS] | Reduce Output Operator [RS_95] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Group By Operator [GBY_94] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Select Operator [SEL_90] | outputColumnNames:["_col0","_col1"] | Filter Operator [FIL_160] | predicate:value is not null (type: boolean) | TableScan [TS_89] | alias:y |<-Reducer 27 [CONTAINS] Reduce Output Operator [RS_95] key expressions:_col0 (type: string), _col1 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string) sort order:++ Group By Operator [GBY_94] keys:_col0 (type: string), _col1 (type: string) outputColumnNames:["_col0","_col1"] Group By Operator [GBY_87] | keys:KEY._col0 (type: string), KEY._col1 (type: string) | outputColumnNames:["_col0","_col1"] |<-Union 26 [SIMPLE_EDGE] |<-Reducer 25 [CONTAINS] | Reduce Output Operator [RS_86] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Group By Operator [GBY_85] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Group By Operator [GBY_78] | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | outputColumnNames:["_col0","_col1"] | |<-Union 24 [SIMPLE_EDGE] | |<-Map 30 [CONTAINS] | | Reduce Output Operator [RS_77] | | key expressions:_col0 (type: string), _col1 (type: string) | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | sort order:++ | | Group By Operator [GBY_76] | | keys:_col0 (type: string), _col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Select Operator [SEL_72] | | outputColumnNames:["_col0","_col1"] | | Filter Operator [FIL_158] | | predicate:value is not null (type: boolean) | | TableScan [TS_71] | | alias:y | |<-Map 23 [CONTAINS] | Reduce Output Operator [RS_77] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Group By Operator [GBY_76] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Select Operator [SEL_70] | outputColumnNames:["_col0","_col1"] | Filter Operator [FIL_157] | predicate:value is not null (type: boolean) | TableScan [TS_69] | alias:x |<-Map 31 [CONTAINS] Reduce Output Operator [RS_86] key expressions:_col0 (type: string), _col1 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string) sort order:++ Group By Operator [GBY_85] keys:_col0 (type: string), _col1 (type: string) outputColumnNames:["_col0","_col1"] Select Operator [SEL_81] outputColumnNames:["_col0","_col1"] Filter Operator [FIL_159] predicate:value is not null (type: boolean) TableScan [TS_80] alias:y PREHOOK: query: CREATE TABLE a(key STRING, value STRING) STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@a POSTHOOK: query: CREATE TABLE a(key STRING, value STRING) STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@a PREHOOK: query: CREATE TABLE b(key STRING, value STRING) STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@b POSTHOOK: query: CREATE TABLE b(key STRING, value STRING) STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@b PREHOOK: query: CREATE TABLE c(key STRING, value STRING) STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@c POSTHOOK: query: CREATE TABLE c(key STRING, value STRING) STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@c PREHOOK: query: explain from ( SELECT x.key, y.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN (select * from src1 union all select * from src)z ON (x.value = z.value) union all SELECT x.key, y.value FROM src x JOIN src y ON (x.key = y.key) JOIN (select key, value from src1 union all select key, value from src union all select key, value from src)z ON (x.value = z.value) union all SELECT x.key, y.value FROM src1 x JOIN src1 y ON (x.key = y.key) JOIN (select key, value from src1 union all select key, value from src union all select key, value from src union all select key, value from src)z ON (x.value = z.value) ) tmp INSERT OVERWRITE TABLE a SELECT tmp.key, tmp.value INSERT OVERWRITE TABLE b SELECT tmp.key, tmp.value INSERT OVERWRITE TABLE c SELECT tmp.key, tmp.value PREHOOK: type: QUERY POSTHOOK: query: explain from ( SELECT x.key, y.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN (select * from src1 union all select * from src)z ON (x.value = z.value) union all SELECT x.key, y.value FROM src x JOIN src y ON (x.key = y.key) JOIN (select key, value from src1 union all select key, value from src union all select key, value from src)z ON (x.value = z.value) union all SELECT x.key, y.value FROM src1 x JOIN src1 y ON (x.key = y.key) JOIN (select key, value from src1 union all select key, value from src union all select key, value from src union all select key, value from src)z ON (x.value = z.value) ) tmp INSERT OVERWRITE TABLE a SELECT tmp.key, tmp.value INSERT OVERWRITE TABLE b SELECT tmp.key, tmp.value INSERT OVERWRITE TABLE c SELECT tmp.key, tmp.value POSTHOOK: type: QUERY Plan not optimized by CBO. Vertex dependency in root stage Map 12 <- Union 9 (CONTAINS) Reducer 14 <- Map 13 (SIMPLE_EDGE), Map 15 (SIMPLE_EDGE) Map 11 <- Union 9 (CONTAINS) Map 21 <- Map 20 (BROADCAST_EDGE) Map 1 <- Union 2 (CONTAINS) Reducer 10 <- Reducer 14 (SIMPLE_EDGE), Union 4 (CONTAINS), Union 9 (SIMPLE_EDGE) Map 19 <- Map 21 (BROADCAST_EDGE), Union 4 (CONTAINS) Map 16 <- Map 21 (BROADCAST_EDGE), Union 4 (CONTAINS) Map 18 <- Map 21 (BROADCAST_EDGE), Union 4 (CONTAINS) Map 17 <- Map 21 (BROADCAST_EDGE), Union 4 (CONTAINS) Reducer 3 <- Map 7 (SIMPLE_EDGE), Union 2 (SIMPLE_EDGE), Union 4 (CONTAINS) Map 5 <- Union 2 (CONTAINS) Map 7 <- Map 6 (BROADCAST_EDGE) Map 8 <- Union 9 (CONTAINS) Stage-7 Stats-Aggr Operator Stage-2 Move Operator table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.c","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Stage-4 Dependency Collection{} Stage-3 Union 4 |<-Reducer 10 [CONTAINS] | File Output Operator [FS_62] | compressed:false | table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.a","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} | Select Operator [SEL_37] | outputColumnNames:["_col0","_col1"] | Merge Join Operator [MERGEJOIN_107] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"1":"_col1 (type: string)","0":"_col1 (type: string)"} | | outputColumnNames:["_col0","_col6"] | |<-Reducer 14 [SIMPLE_EDGE] | | Reduce Output Operator [RS_33] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ | | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col0 (type: string), _col6 (type: string) | | Merge Join Operator [MERGEJOIN_104] | | | condition map:[{"":"Inner Join 0 to 1"}] | | | keys:{"1":"key (type: string)","0":"key (type: string)"} | | | outputColumnNames:["_col0","_col1","_col6"] | | | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE | | |<-Map 13 [SIMPLE_EDGE] | | | Reduce Output Operator [RS_28] | | | key expressions:key (type: string) | | | Map-reduce partition columns:key (type: string) | | | sort order:+ | | | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE | | | value expressions:value (type: string) | | | Filter Operator [FIL_95] | | | predicate:(key is not null and value is not null) (type: boolean) | | | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE | | | TableScan [TS_25] | | | alias:x | | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | | |<-Map 15 [SIMPLE_EDGE] | | Reduce Output Operator [RS_30] | | key expressions:key (type: string) | | Map-reduce partition columns:key (type: string) | | sort order:+ | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | | value expressions:value (type: string) | | Filter Operator [FIL_96] | | predicate:key is not null (type: boolean) | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | | TableScan [TS_26] | | alias:y | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | |<-Union 9 [SIMPLE_EDGE] | |<-Map 12 [CONTAINS] | | Reduce Output Operator [RS_35] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ | | Select Operator [SEL_24] | | outputColumnNames:["_col1"] | | Filter Operator [FIL_94] | | predicate:value is not null (type: boolean) | | TableScan [TS_23] | | alias:src | |<-Map 11 [CONTAINS] | | Reduce Output Operator [RS_35] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ | | Select Operator [SEL_21] | | outputColumnNames:["_col1"] | | Filter Operator [FIL_93] | | predicate:value is not null (type: boolean) | | TableScan [TS_20] | | alias:src | |<-Map 8 [CONTAINS] | Reduce Output Operator [RS_35] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ | Select Operator [SEL_19] | outputColumnNames:["_col1"] | Filter Operator [FIL_92] | predicate:value is not null (type: boolean) | TableScan [TS_18] | alias:src1 | File Output Operator [FS_64] | compressed:false | table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.b","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} | Please refer to the previous Select Operator [SEL_37] | File Output Operator [FS_66] | compressed:false | table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.c","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} | Please refer to the previous Select Operator [SEL_37] |<-Map 19 [CONTAINS] | File Output Operator [FS_62] | compressed:false | table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.a","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} | Select Operator [SEL_60] | outputColumnNames:["_col0","_col1"] | Map Join Operator [MAPJOIN_108] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"Map 21":"_col1 (type: string)","Map 19":"_col1 (type: string)"} | | outputColumnNames:["_col0","_col6"] | |<-Map 21 [BROADCAST_EDGE] | | Reduce Output Operator [RS_56] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ | | Statistics:Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col0 (type: string), _col6 (type: string) | | Map Join Operator [MAPJOIN_105] | | | condition map:[{"":"Inner Join 0 to 1"}] | | | keys:{"Map 21":"key (type: string)","Map 20":"key (type: string)"} | | | outputColumnNames:["_col0","_col1","_col6"] | | | Statistics:Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE | | |<-Map 20 [BROADCAST_EDGE] | | | Reduce Output Operator [RS_51] | | | key expressions:key (type: string) | | | Map-reduce partition columns:key (type: string) | | | sort order:+ | | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | | value expressions:value (type: string) | | | Filter Operator [FIL_101] | | | predicate:(key is not null and value is not null) (type: boolean) | | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | | TableScan [TS_48] | | | alias:x | | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | | |<-Filter Operator [FIL_102] | | predicate:key is not null (type: boolean) | | Statistics:Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE | | TableScan [TS_49] | | alias:y | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | | Reduce Output Operator [RS_111] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ | | Statistics:Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col0 (type: string), _col6 (type: string) | | Please refer to the previous Map Join Operator [MAPJOIN_105] | | Reduce Output Operator [RS_112] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ | | Statistics:Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col0 (type: string), _col6 (type: string) | | Please refer to the previous Map Join Operator [MAPJOIN_105] | | Reduce Output Operator [RS_113] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ | | Statistics:Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col0 (type: string), _col6 (type: string) | | Please refer to the previous Map Join Operator [MAPJOIN_105] | |<-Select Operator [SEL_47] | outputColumnNames:["_col1"] | Filter Operator [FIL_100] | predicate:value is not null (type: boolean) | TableScan [TS_46] | alias:src | File Output Operator [FS_64] | compressed:false | table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.b","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} | Please refer to the previous Select Operator [SEL_60] | File Output Operator [FS_66] | compressed:false | table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.c","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} | Please refer to the previous Select Operator [SEL_60] |<-Map 16 [CONTAINS] | File Output Operator [FS_62] | compressed:false | table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.a","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} | Select Operator [SEL_60] | outputColumnNames:["_col0","_col1"] | Map Join Operator [MAPJOIN_108] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"Map 21":"_col1 (type: string)","Map 16":"_col1 (type: string)"} | | outputColumnNames:["_col0","_col6"] | |<- Please refer to the previous Map 21 [BROADCAST_EDGE] | |<-Select Operator [SEL_40] | outputColumnNames:["_col1"] | Filter Operator [FIL_97] | predicate:value is not null (type: boolean) | TableScan [TS_39] | alias:src1 | File Output Operator [FS_64] | compressed:false | table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.b","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} | Please refer to the previous Select Operator [SEL_60] | File Output Operator [FS_66] | compressed:false | table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.c","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} | Please refer to the previous Select Operator [SEL_60] |<-Map 18 [CONTAINS] | File Output Operator [FS_62] | compressed:false | table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.a","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} | Select Operator [SEL_60] | outputColumnNames:["_col0","_col1"] | Map Join Operator [MAPJOIN_108] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"Map 21":"_col1 (type: string)","Map 18":"_col1 (type: string)"} | | outputColumnNames:["_col0","_col6"] | |<- Please refer to the previous Map 21 [BROADCAST_EDGE] | |<-Select Operator [SEL_45] | outputColumnNames:["_col1"] | Filter Operator [FIL_99] | predicate:value is not null (type: boolean) | TableScan [TS_44] | alias:src | File Output Operator [FS_64] | compressed:false | table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.b","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} | Please refer to the previous Select Operator [SEL_60] | File Output Operator [FS_66] | compressed:false | table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.c","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} | Please refer to the previous Select Operator [SEL_60] |<-Map 17 [CONTAINS] | File Output Operator [FS_62] | compressed:false | table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.a","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} | Select Operator [SEL_60] | outputColumnNames:["_col0","_col1"] | Map Join Operator [MAPJOIN_108] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"Map 21":"_col1 (type: string)","Map 17":"_col1 (type: string)"} | | outputColumnNames:["_col0","_col6"] | |<- Please refer to the previous Map 21 [BROADCAST_EDGE] | |<-Select Operator [SEL_42] | outputColumnNames:["_col1"] | Filter Operator [FIL_98] | predicate:value is not null (type: boolean) | TableScan [TS_41] | alias:src | File Output Operator [FS_64] | compressed:false | table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.b","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} | Please refer to the previous Select Operator [SEL_60] | File Output Operator [FS_66] | compressed:false | table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.c","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} | Please refer to the previous Select Operator [SEL_60] |<-Reducer 3 [CONTAINS] File Output Operator [FS_62] compressed:false table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.a","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_17] outputColumnNames:["_col0","_col1"] Merge Join Operator [MERGEJOIN_106] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"1":"_col1 (type: string)","0":"_col1 (type: string)"} | outputColumnNames:["_col0","_col6"] |<-Map 7 [SIMPLE_EDGE] | Reduce Output Operator [RS_13] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE | value expressions:_col0 (type: string), _col6 (type: string) | Map Join Operator [MAPJOIN_103] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"Map 7":"key (type: string)","Map 6":"key (type: string)"} | | outputColumnNames:["_col0","_col1","_col6"] | | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE | |<-Map 6 [BROADCAST_EDGE] | | Reduce Output Operator [RS_8] | | key expressions:key (type: string) | | Map-reduce partition columns:key (type: string) | | sort order:+ | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | value expressions:value (type: string) | | Filter Operator [FIL_90] | | predicate:(key is not null and value is not null) (type: boolean) | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | TableScan [TS_5] | | alias:x | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | |<-Filter Operator [FIL_91] | predicate:key is not null (type: boolean) | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_6] | alias:y | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE |<-Union 2 [SIMPLE_EDGE] |<-Map 1 [CONTAINS] | Reduce Output Operator [RS_15] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ | Select Operator [SEL_1] | outputColumnNames:["_col1"] | Filter Operator [FIL_88] | predicate:value is not null (type: boolean) | TableScan [TS_0] | alias:src1 |<-Map 5 [CONTAINS] Reduce Output Operator [RS_15] key expressions:_col1 (type: string) Map-reduce partition columns:_col1 (type: string) sort order:+ Select Operator [SEL_3] outputColumnNames:["_col1"] Filter Operator [FIL_89] predicate:value is not null (type: boolean) TableScan [TS_2] alias:src File Output Operator [FS_64] compressed:false table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.b","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Please refer to the previous Select Operator [SEL_17] File Output Operator [FS_66] compressed:false table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.c","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Please refer to the previous Select Operator [SEL_17] Stage-6 Stats-Aggr Operator Stage-1 Move Operator table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.b","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Please refer to the previous Stage-4 Stage-5 Stats-Aggr Operator Stage-0 Move Operator table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.a","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Please refer to the previous Stage-4 PREHOOK: query: explain FROM ( SELECT x.key as key, y.value as value from src1 x JOIN src y ON (x.key = y.key) JOIN (select * from src1 union select * from src)z ON (x.value = z.value) union SELECT x.key as key, y.value as value from src x JOIN src y ON (x.key = y.key) JOIN (select key, value from src1 union select key, value from src union select key, value from src)z ON (x.value = z.value) union SELECT x.key as key, y.value as value from src1 x JOIN src1 y ON (x.key = y.key) JOIN (select key, value from src1 union select key, value from src union select key, value from src union select key, value from src)z ON (x.value = z.value) ) tmp INSERT OVERWRITE TABLE a SELECT tmp.key, tmp.value INSERT OVERWRITE TABLE b SELECT tmp.key, tmp.value INSERT OVERWRITE TABLE c SELECT tmp.key, tmp.value PREHOOK: type: QUERY POSTHOOK: query: explain FROM ( SELECT x.key as key, y.value as value from src1 x JOIN src y ON (x.key = y.key) JOIN (select * from src1 union select * from src)z ON (x.value = z.value) union SELECT x.key as key, y.value as value from src x JOIN src y ON (x.key = y.key) JOIN (select key, value from src1 union select key, value from src union select key, value from src)z ON (x.value = z.value) union SELECT x.key as key, y.value as value from src1 x JOIN src1 y ON (x.key = y.key) JOIN (select key, value from src1 union select key, value from src union select key, value from src union select key, value from src)z ON (x.value = z.value) ) tmp INSERT OVERWRITE TABLE a SELECT tmp.key, tmp.value INSERT OVERWRITE TABLE b SELECT tmp.key, tmp.value INSERT OVERWRITE TABLE c SELECT tmp.key, tmp.value POSTHOOK: type: QUERY Plan not optimized by CBO. Vertex dependency in root stage Map 12 <- Union 13 (CONTAINS) Map 30 <- Union 24 (CONTAINS) Map 11 <- Map 10 (BROADCAST_EDGE) Reducer 14 <- Union 13 (SIMPLE_EDGE), Union 15 (CONTAINS) Map 23 <- Union 24 (CONTAINS) Map 32 <- Union 28 (CONTAINS) Reducer 25 <- Union 24 (SIMPLE_EDGE), Union 26 (CONTAINS) Map 31 <- Union 26 (CONTAINS) Map 34 <- Map 33 (BROADCAST_EDGE) Map 1 <- Union 2 (CONTAINS) Reducer 21 <- Map 20 (SIMPLE_EDGE), Map 22 (SIMPLE_EDGE) Reducer 4 <- Map 11 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE), Union 5 (CONTAINS) Map 19 <- Union 15 (CONTAINS) Reducer 6 <- Union 5 (SIMPLE_EDGE), Union 7 (CONTAINS) Reducer 17 <- Reducer 16 (SIMPLE_EDGE), Reducer 21 (SIMPLE_EDGE), Union 5 (CONTAINS) Reducer 8 <- Union 7 (SIMPLE_EDGE) Reducer 27 <- Union 26 (SIMPLE_EDGE), Union 28 (CONTAINS) Map 18 <- Union 13 (CONTAINS) Reducer 29 <- Map 34 (BROADCAST_EDGE), Union 28 (SIMPLE_EDGE), Union 7 (CONTAINS) Reducer 16 <- Union 15 (SIMPLE_EDGE) Reducer 3 <- Union 2 (SIMPLE_EDGE) Map 9 <- Union 2 (CONTAINS) Stage-7 Stats-Aggr Operator Stage-2 Move Operator table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.c","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Stage-4 Dependency Collection{} Stage-3 Reducer 8 File Output Operator [FS_114] compressed:false Statistics:Num rows: 272 Data size: 2889 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.a","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Group By Operator [GBY_111] | keys:KEY._col0 (type: string), KEY._col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 272 Data size: 2889 Basic stats: COMPLETE Column stats: NONE |<-Union 7 [SIMPLE_EDGE] |<-Reducer 6 [CONTAINS] | Reduce Output Operator [RS_110] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Group By Operator [GBY_109] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Group By Operator [GBY_62] | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | outputColumnNames:["_col0","_col1"] | |<-Union 5 [SIMPLE_EDGE] | |<-Reducer 4 [CONTAINS] | | Reduce Output Operator [RS_61] | | key expressions:_col0 (type: string), _col1 (type: string) | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | sort order:++ | | Group By Operator [GBY_60] | | keys:_col0 (type: string), _col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Select Operator [SEL_23] | | outputColumnNames:["_col0","_col1"] | | Merge Join Operator [MERGEJOIN_158] | | | condition map:[{"":"Inner Join 0 to 1"}] | | | keys:{"1":"_col1 (type: string)","0":"_col1 (type: string)"} | | | outputColumnNames:["_col0","_col6"] | | |<-Map 11 [SIMPLE_EDGE] | | | Reduce Output Operator [RS_19] | | | key expressions:_col1 (type: string) | | | Map-reduce partition columns:_col1 (type: string) | | | sort order:+ | | | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE | | | value expressions:_col0 (type: string), _col6 (type: string) | | | Map Join Operator [MAPJOIN_155] | | | | condition map:[{"":"Inner Join 0 to 1"}] | | | | keys:{"Map 11":"key (type: string)","Map 10":"key (type: string)"} | | | | outputColumnNames:["_col0","_col1","_col6"] | | | | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE | | | |<-Map 10 [BROADCAST_EDGE] | | | | Reduce Output Operator [RS_14] | | | | key expressions:key (type: string) | | | | Map-reduce partition columns:key (type: string) | | | | sort order:+ | | | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | | | value expressions:value (type: string) | | | | Filter Operator [FIL_142] | | | | predicate:(key is not null and value is not null) (type: boolean) | | | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | | | TableScan [TS_11] | | | | alias:x | | | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | | | |<-Filter Operator [FIL_143] | | | predicate:key is not null (type: boolean) | | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | | | TableScan [TS_12] | | | alias:y | | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | | |<-Reducer 3 [SIMPLE_EDGE] | | Reduce Output Operator [RS_21] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ | | Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE | | Select Operator [SEL_10] | | outputColumnNames:["_col1"] | | Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE | | Group By Operator [GBY_9] | | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | | outputColumnNames:["_col0","_col1"] | | | Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE | | |<-Union 2 [SIMPLE_EDGE] | | |<-Map 1 [CONTAINS] | | | 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:++ | | | Group By Operator [GBY_7] | | | keys:_col0 (type: string), _col1 (type: string) | | | outputColumnNames:["_col0","_col1"] | | | Select Operator [SEL_1] | | | outputColumnNames:["_col0","_col1"] | | | Filter Operator [FIL_140] | | | predicate:value is not null (type: boolean) | | | TableScan [TS_0] | | | alias:src1 | | |<-Map 9 [CONTAINS] | | 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:++ | | Group By Operator [GBY_7] | | keys:_col0 (type: string), _col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Select Operator [SEL_3] | | outputColumnNames:["_col0","_col1"] | | Filter Operator [FIL_141] | | predicate:value is not null (type: boolean) | | TableScan [TS_2] | | alias:src | |<-Reducer 17 [CONTAINS] | Reduce Output Operator [RS_61] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Group By Operator [GBY_60] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Select Operator [SEL_56] | outputColumnNames:["_col0","_col1"] | Merge Join Operator [MERGEJOIN_159] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"1":"_col1 (type: string)","0":"_col1 (type: string)"} | | outputColumnNames:["_col0","_col6"] | |<-Reducer 16 [SIMPLE_EDGE] | | Reduce Output Operator [RS_54] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ | | Statistics:Num rows: 190 Data size: 2008 Basic stats: COMPLETE Column stats: NONE | | Select Operator [SEL_43] | | outputColumnNames:["_col1"] | | Statistics:Num rows: 190 Data size: 2008 Basic stats: COMPLETE Column stats: NONE | | Group By Operator [GBY_42] | | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | | outputColumnNames:["_col0","_col1"] | | | Statistics:Num rows: 190 Data size: 2008 Basic stats: COMPLETE Column stats: NONE | | |<-Union 15 [SIMPLE_EDGE] | | |<-Reducer 14 [CONTAINS] | | | Reduce Output Operator [RS_41] | | | key expressions:_col0 (type: string), _col1 (type: string) | | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | | sort order:++ | | | Group By Operator [GBY_40] | | | keys:_col0 (type: string), _col1 (type: string) | | | outputColumnNames:["_col0","_col1"] | | | Group By Operator [GBY_33] | | | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | | | outputColumnNames:["_col0","_col1"] | | | |<-Union 13 [SIMPLE_EDGE] | | | |<-Map 12 [CONTAINS] | | | | Reduce Output Operator [RS_32] | | | | key expressions:_col0 (type: string), _col1 (type: string) | | | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | | | sort order:++ | | | | Group By Operator [GBY_31] | | | | keys:_col0 (type: string), _col1 (type: string) | | | | outputColumnNames:["_col0","_col1"] | | | | Select Operator [SEL_25] | | | | outputColumnNames:["_col0","_col1"] | | | | Filter Operator [FIL_144] | | | | predicate:value is not null (type: boolean) | | | | TableScan [TS_24] | | | | alias:src1 | | | |<-Map 18 [CONTAINS] | | | Reduce Output Operator [RS_32] | | | key expressions:_col0 (type: string), _col1 (type: string) | | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | | sort order:++ | | | Group By Operator [GBY_31] | | | keys:_col0 (type: string), _col1 (type: string) | | | outputColumnNames:["_col0","_col1"] | | | Select Operator [SEL_27] | | | outputColumnNames:["_col0","_col1"] | | | Filter Operator [FIL_145] | | | predicate:value is not null (type: boolean) | | | TableScan [TS_26] | | | alias:src | | |<-Map 19 [CONTAINS] | | Reduce Output Operator [RS_41] | | key expressions:_col0 (type: string), _col1 (type: string) | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | sort order:++ | | Group By Operator [GBY_40] | | keys:_col0 (type: string), _col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Select Operator [SEL_36] | | outputColumnNames:["_col0","_col1"] | | Filter Operator [FIL_146] | | predicate:value is not null (type: boolean) | | TableScan [TS_35] | | alias:src | |<-Reducer 21 [SIMPLE_EDGE] | Reduce Output Operator [RS_52] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE | value expressions:_col0 (type: string), _col6 (type: string) | Merge Join Operator [MERGEJOIN_156] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"1":"key (type: string)","0":"key (type: string)"} | | outputColumnNames:["_col0","_col1","_col6"] | | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE | |<-Map 20 [SIMPLE_EDGE] | | Reduce Output Operator [RS_47] | | key expressions:key (type: string) | | Map-reduce partition columns:key (type: string) | | sort order:+ | | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE | | value expressions:value (type: string) | | Filter Operator [FIL_147] | | predicate:(key is not null and value is not null) (type: boolean) | | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE | | TableScan [TS_44] | | alias:x | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | |<-Map 22 [SIMPLE_EDGE] | Reduce Output Operator [RS_49] | key expressions:key (type: string) | Map-reduce partition columns:key (type: string) | sort order:+ | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | value expressions:value (type: string) | Filter Operator [FIL_148] | predicate:key is not null (type: boolean) | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_45] | alias:y | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE |<-Reducer 29 [CONTAINS] Reduce Output Operator [RS_110] key expressions:_col0 (type: string), _col1 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string) sort order:++ Group By Operator [GBY_109] keys:_col0 (type: string), _col1 (type: string) outputColumnNames:["_col0","_col1"] Select Operator [SEL_105] outputColumnNames:["_col0","_col1"] Map Join Operator [MAPJOIN_160] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"Map 34":"_col1 (type: string)","Reducer 29":"_col1 (type: string)"} | outputColumnNames:["_col0","_col6"] |<-Map 34 [BROADCAST_EDGE] | Reduce Output Operator [RS_101] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ | Statistics:Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE | value expressions:_col0 (type: string), _col6 (type: string) | Map Join Operator [MAPJOIN_157] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"Map 34":"key (type: string)","Map 33":"key (type: string)"} | | outputColumnNames:["_col0","_col1","_col6"] | | Statistics:Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE | |<-Map 33 [BROADCAST_EDGE] | | Reduce Output Operator [RS_96] | | key expressions:key (type: string) | | Map-reduce partition columns:key (type: string) | | sort order:+ | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | value expressions:value (type: string) | | Filter Operator [FIL_153] | | predicate:(key is not null and value is not null) (type: boolean) | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE | | TableScan [TS_93] | | alias:x | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | |<-Filter Operator [FIL_154] | predicate:key is not null (type: boolean) | Statistics:Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_94] | alias:y | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE |<-Select Operator [SEL_92] outputColumnNames:["_col1"] Group By Operator [GBY_91] | keys:KEY._col0 (type: string), KEY._col1 (type: string) | outputColumnNames:["_col0","_col1"] |<-Union 28 [SIMPLE_EDGE] |<-Map 32 [CONTAINS] | Reduce Output Operator [RS_90] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Group By Operator [GBY_89] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Select Operator [SEL_85] | outputColumnNames:["_col0","_col1"] | Filter Operator [FIL_152] | predicate:value is not null (type: boolean) | TableScan [TS_84] | alias:src |<-Reducer 27 [CONTAINS] Reduce Output Operator [RS_90] key expressions:_col0 (type: string), _col1 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string) sort order:++ Group By Operator [GBY_89] keys:_col0 (type: string), _col1 (type: string) outputColumnNames:["_col0","_col1"] Group By Operator [GBY_82] | keys:KEY._col0 (type: string), KEY._col1 (type: string) | outputColumnNames:["_col0","_col1"] |<-Union 26 [SIMPLE_EDGE] |<-Reducer 25 [CONTAINS] | Reduce Output Operator [RS_81] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Group By Operator [GBY_80] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Group By Operator [GBY_73] | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | outputColumnNames:["_col0","_col1"] | |<-Union 24 [SIMPLE_EDGE] | |<-Map 30 [CONTAINS] | | Reduce Output Operator [RS_72] | | key expressions:_col0 (type: string), _col1 (type: string) | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | sort order:++ | | Group By Operator [GBY_71] | | keys:_col0 (type: string), _col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Select Operator [SEL_67] | | outputColumnNames:["_col0","_col1"] | | Filter Operator [FIL_150] | | predicate:value is not null (type: boolean) | | TableScan [TS_66] | | alias:src | |<-Map 23 [CONTAINS] | Reduce Output Operator [RS_72] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Group By Operator [GBY_71] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Select Operator [SEL_65] | outputColumnNames:["_col0","_col1"] | Filter Operator [FIL_149] | predicate:value is not null (type: boolean) | TableScan [TS_64] | alias:src1 |<-Map 31 [CONTAINS] Reduce Output Operator [RS_81] key expressions:_col0 (type: string), _col1 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string) sort order:++ Group By Operator [GBY_80] keys:_col0 (type: string), _col1 (type: string) outputColumnNames:["_col0","_col1"] Select Operator [SEL_76] outputColumnNames:["_col0","_col1"] Filter Operator [FIL_151] predicate:value is not null (type: boolean) TableScan [TS_75] alias:src File Output Operator [FS_116] compressed:false Statistics:Num rows: 272 Data size: 2889 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.b","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Please refer to the previous Group By Operator [GBY_111] File Output Operator [FS_118] compressed:false Statistics:Num rows: 272 Data size: 2889 Basic stats: COMPLETE Column stats: NONE table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.c","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Please refer to the previous Group By Operator [GBY_111] Stage-6 Stats-Aggr Operator Stage-1 Move Operator table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.b","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Please refer to the previous Stage-4 Stage-5 Stats-Aggr Operator Stage-0 Move Operator table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.a","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Please refer to the previous Stage-4 PREHOOK: query: CREATE TABLE DEST1(key STRING, value STRING) STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@DEST1 POSTHOOK: query: CREATE TABLE DEST1(key STRING, value STRING) STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@DEST1 PREHOOK: query: CREATE TABLE DEST2(key STRING, val1 STRING, val2 STRING) STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@DEST2 POSTHOOK: query: CREATE TABLE DEST2(key STRING, val1 STRING, val2 STRING) STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@DEST2 PREHOOK: query: explain FROM (select 'tst1' as key, cast(count(1) as string) as value from src s1 UNION DISTINCT select s2.key as key, s2.value as value from src s2) unionsrc INSERT OVERWRITE TABLE DEST1 SELECT unionsrc.key, COUNT(DISTINCT SUBSTR(unionsrc.value,5)) GROUP BY unionsrc.key INSERT OVERWRITE TABLE DEST2 SELECT unionsrc.key, unionsrc.value, COUNT(DISTINCT SUBSTR(unionsrc.value,5)) GROUP BY unionsrc.key, unionsrc.value PREHOOK: type: QUERY POSTHOOK: query: explain FROM (select 'tst1' as key, cast(count(1) as string) as value from src s1 UNION DISTINCT select s2.key as key, s2.value as value from src s2) unionsrc INSERT OVERWRITE TABLE DEST1 SELECT unionsrc.key, COUNT(DISTINCT SUBSTR(unionsrc.value,5)) GROUP BY unionsrc.key INSERT OVERWRITE TABLE DEST2 SELECT unionsrc.key, unionsrc.value, COUNT(DISTINCT SUBSTR(unionsrc.value,5)) GROUP BY unionsrc.key, unionsrc.value POSTHOOK: type: QUERY Plan not 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) Map 6 <- Union 3 (CONTAINS) Stage-5 Stats-Aggr Operator Stage-1 Move Operator table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.dest2","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Stage-3 Dependency Collection{} Stage-2 Reducer 5 File Output Operator [FS_20] compressed:false Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: PARTIAL table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.dest1","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Group By Operator [GBY_18] | aggregations:["count(DISTINCT KEY._col1:0._col0)"] | keys:KEY._col0 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: PARTIAL |<-Reducer 4 [SIMPLE_EDGE] Reduce Output Operator [RS_17] key expressions:_col0 (type: string), _col1 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:++ Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: PARTIAL Group By Operator [GBY_16] aggregations:["count(DISTINCT substr(_col1, 5))"] keys:_col0 (type: string), substr(_col1, 5) (type: string) outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: PARTIAL Group By Operator [GBY_13] | keys:KEY._col0 (type: string), KEY._col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: PARTIAL |<-Union 3 [SIMPLE_EDGE] |<-Reducer 2 [CONTAINS] | Reduce Output Operator [RS_12] | key expressions:_col0 (type: string), _col1 (type: string), substr(_col1, 5) (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:+++ | Group By Operator [GBY_11] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Select Operator [SEL_5] | outputColumnNames:["_col0","_col1"] | Group By Operator [GBY_4] | | aggregations:["count(VALUE._col0)"] | | outputColumnNames:["_col0"] | |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_3] | sort order: | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col0 (type: bigint) | Group By Operator [GBY_2] | 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:s1 | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 6 [CONTAINS] Reduce Output Operator [RS_12] key expressions:_col0 (type: string), _col1 (type: string), substr(_col1, 5) (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string) sort order:+++ Group By Operator [GBY_11] keys:_col0 (type: string), _col1 (type: string) outputColumnNames:["_col0","_col1"] Select Operator [SEL_7] outputColumnNames:["_col0","_col1"] TableScan [TS_6] alias:s2 File Output Operator [FS_26] compressed:false Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: PARTIAL table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.dest2","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Select Operator [SEL_25] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: PARTIAL Group By Operator [GBY_24] aggregations:["count(DISTINCT substr(_col1, 5))"] keys:_col0 (type: string), _col1 (type: string) outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: PARTIAL Please refer to the previous Group By Operator [GBY_13] Stage-4 Stats-Aggr Operator Stage-0 Move Operator table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.dest1","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 FROM UNIQUEJOIN PRESERVE src a (a.key), PRESERVE src1 b (b.key), PRESERVE srcpart c (c.key) SELECT a.key, b.key, c.key PREHOOK: type: QUERY POSTHOOK: query: EXPLAIN FROM UNIQUEJOIN PRESERVE src a (a.key), PRESERVE src1 b (b.key), PRESERVE srcpart c (c.key) SELECT a.key, b.key, c.key POSTHOOK: type: QUERY Plan not optimized by CBO due to missing feature [Unique_join]. 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:false Statistics:Num rows: 4400 Data size: 46745 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"] Statistics:Num rows: 4400 Data size: 46745 Basic stats: COMPLETE Column stats: NONE Merge Join Operator [MERGEJOIN_9] | condition map:[{"":"Unique Join0 to 0"},{"":"Unique Join0 to 0"},{"":"Unique Join0 to 0"}] | keys:{"2":"key (type: string)","1":"key (type: string)","0":"key (type: string)"} | outputColumnNames:["_col0","_col5","_col10"] | Statistics:Num rows: 4400 Data size: 46745 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_3] | key expressions:key (type: string) | Map-reduce partition columns:key (type: string) | sort order:+ | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_0] | alias:a | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE |<-Map 3 [SIMPLE_EDGE] | Reduce Output Operator [RS_4] | key expressions:key (type: string) | Map-reduce partition columns:key (type: string) | sort order:+ | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_1] | alias:b | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE |<-Map 4 [SIMPLE_EDGE] Reduce Output Operator [RS_5] key expressions:key (type: string) Map-reduce partition columns:key (type: string) sort order:+ Statistics:Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE TableScan [TS_2] alias:c Statistics:Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: EXPLAIN SELECT TRANSFORM(a.key, a.value) USING 'cat' AS (tkey, tvalue) FROM src a join src b on a.key = b.key PREHOOK: type: QUERY POSTHOOK: query: EXPLAIN SELECT TRANSFORM(a.key, a.value) USING 'cat' AS (tkey, tvalue) FROM src a join src b on a.key = b.key POSTHOOK: type: QUERY Plan not 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:false Statistics:Num rows: 275 Data size: 2921 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"} Transform Operator [SCR_8] command:cat output info:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Merge Join Operator [MERGEJOIN_14] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"1":"key (type: string)","0":"key (type: string)"} | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_3] | key expressions:key (type: string) | Map-reduce partition columns:key (type: string) | sort order:+ | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | value expressions:value (type: string) | Filter Operator [FIL_12] | predicate:key is not null (type: boolean) | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_0] | alias:a | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE |<-Map 3 [SIMPLE_EDGE] Reduce Output Operator [RS_5] key expressions:key (type: string) Map-reduce partition columns:key (type: string) sort order:+ Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Filter Operator [FIL_13] predicate:key is not null (type: boolean) Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan [TS_1] alias:b Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE