PREHOOK: query: CREATE TABLE T1(key INT, val STRING) PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@T1 POSTHOOK: query: CREATE TABLE T1(key INT, val STRING) POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@T1 PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/kv1.txt' INTO TABLE T1 PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@t1 POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/kv1.txt' INTO TABLE T1 POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@t1 PREHOOK: query: CREATE TABLE T2(key INT, val STRING) PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@T2 POSTHOOK: query: CREATE TABLE T2(key INT, val STRING) POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@T2 PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/kv2.txt' INTO TABLE T2 PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@t2 POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/kv2.txt' INTO TABLE T2 POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@t2 PREHOOK: query: CREATE TABLE T3(key INT, val STRING) PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@T3 POSTHOOK: query: CREATE TABLE T3(key INT, val STRING) POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@T3 PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/kv3.txt' INTO TABLE T3 PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@t3 POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/kv3.txt' INTO TABLE T3 POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@t3 PREHOOK: query: CREATE TABLE T4(key INT, val STRING) PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@T4 POSTHOOK: query: CREATE TABLE T4(key INT, val STRING) POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@T4 PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/kv5.txt' INTO TABLE T4 PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@t4 POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/kv5.txt' INTO TABLE T4 POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@t4 PREHOOK: query: CREATE TABLE dest_co1(key INT, val STRING) PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@dest_co1 POSTHOOK: query: CREATE TABLE dest_co1(key INT, val STRING) POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@dest_co1 PREHOOK: query: CREATE TABLE dest_co2(key INT, val STRING) PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@dest_co2 POSTHOOK: query: CREATE TABLE dest_co2(key INT, val STRING) POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@dest_co2 PREHOOK: query: CREATE TABLE dest_co3(key INT, val STRING) PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@dest_co3 POSTHOOK: query: CREATE TABLE dest_co3(key INT, val STRING) POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@dest_co3 PREHOOK: query: -- When Correlation Optimizer is turned off, 3 MR jobs are needed. -- When Correlation Optimizer is turned on, only a single MR job is needed. EXPLAIN INSERT OVERWRITE TABLE dest_co1 SELECT b.key, d.val FROM (SELECT x.key, x.val FROM T1 x JOIN T2 y ON (x.key = y.key)) b JOIN (SELECT m.key, n.val FROM T3 m JOIN T4 n ON (m.key = n.key)) d ON b.key = d.key PREHOOK: type: QUERY POSTHOOK: query: -- When Correlation Optimizer is turned off, 3 MR jobs are needed. -- When Correlation Optimizer is turned on, only a single MR job is needed. EXPLAIN INSERT OVERWRITE TABLE dest_co1 SELECT b.key, d.val FROM (SELECT x.key, x.val FROM T1 x JOIN T2 y ON (x.key = y.key)) b JOIN (SELECT m.key, n.val FROM T3 m JOIN T4 n ON (m.key = n.key)) d ON b.key = d.key POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1, Stage-5 Stage-0 depends on stages: Stage-2 Stage-3 depends on stages: Stage-0 Stage-5 is a root stage STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: x Statistics: Num rows: 1453 Data size: 5812 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 727 Data size: 2908 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: int) sort order: + Map-reduce partition columns: key (type: int) Statistics: Num rows: 727 Data size: 2908 Basic stats: COMPLETE Column stats: NONE TableScan alias: y Statistics: Num rows: 1447 Data size: 5791 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 724 Data size: 2897 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: int) sort order: + Map-reduce partition columns: key (type: int) Statistics: Num rows: 724 Data size: 2897 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0 Statistics: Num rows: 799 Data size: 3198 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 799 Data size: 3198 Basic stats: COMPLETE Column stats: NONE TableScan Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 29 Data size: 118 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col3 Statistics: Num rows: 878 Data size: 3517 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col3 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 878 Data size: 3517 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Statistics: Num rows: 878 Data size: 3517 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest_co1 Stage: Stage-0 Move Operator tables: replace: true table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest_co1 Stage: Stage-3 Stats-Aggr Operator Stage: Stage-5 Map Reduce Map Operator Tree: TableScan alias: m Statistics: Num rows: 54 Data size: 216 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 27 Data size: 108 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: int) sort order: + Map-reduce partition columns: key (type: int) Statistics: Num rows: 27 Data size: 108 Basic stats: COMPLETE Column stats: NONE TableScan alias: n Statistics: Num rows: 2 Data size: 280 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 1 Data size: 140 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: int) sort order: + Map-reduce partition columns: key (type: int) Statistics: Num rows: 1 Data size: 140 Basic stats: COMPLETE Column stats: NONE value expressions: val (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0, _col6 Statistics: Num rows: 29 Data size: 118 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col6 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 29 Data size: 118 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe PREHOOK: query: INSERT OVERWRITE TABLE dest_co1 SELECT b.key, d.val FROM (SELECT x.key, x.val FROM T1 x JOIN T2 y ON (x.key = y.key)) b JOIN (SELECT m.key, n.val FROM T3 m JOIN T4 n ON (m.key = n.key)) d ON b.key = d.key PREHOOK: type: QUERY PREHOOK: Input: default@t1 PREHOOK: Input: default@t2 PREHOOK: Input: default@t3 PREHOOK: Input: default@t4 PREHOOK: Output: default@dest_co1 POSTHOOK: query: INSERT OVERWRITE TABLE dest_co1 SELECT b.key, d.val FROM (SELECT x.key, x.val FROM T1 x JOIN T2 y ON (x.key = y.key)) b JOIN (SELECT m.key, n.val FROM T3 m JOIN T4 n ON (m.key = n.key)) d ON b.key = d.key POSTHOOK: type: QUERY POSTHOOK: Input: default@t1 POSTHOOK: Input: default@t2 POSTHOOK: Input: default@t3 POSTHOOK: Input: default@t4 POSTHOOK: Output: default@dest_co1 POSTHOOK: Lineage: dest_co1.key EXPRESSION [(t1)x.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: dest_co1.val SIMPLE [(t4)n.FieldSchema(name:val, type:string, comment:null), ] PREHOOK: query: EXPLAIN INSERT OVERWRITE TABLE dest_co2 SELECT b.key, d.val FROM (SELECT x.key, x.val FROM T1 x JOIN T2 y ON (x.key = y.key)) b JOIN (SELECT m.key, n.val FROM T3 m JOIN T4 n ON (m.key = n.key)) d ON b.key = d.key PREHOOK: type: QUERY POSTHOOK: query: EXPLAIN INSERT OVERWRITE TABLE dest_co2 SELECT b.key, d.val FROM (SELECT x.key, x.val FROM T1 x JOIN T2 y ON (x.key = y.key)) b JOIN (SELECT m.key, n.val FROM T3 m JOIN T4 n ON (m.key = n.key)) d ON b.key = d.key POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 Stage-2 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: x Statistics: Num rows: 1453 Data size: 5812 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 727 Data size: 2908 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: int) sort order: + Map-reduce partition columns: key (type: int) Statistics: Num rows: 727 Data size: 2908 Basic stats: COMPLETE Column stats: NONE TableScan alias: y Statistics: Num rows: 1447 Data size: 5791 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 724 Data size: 2897 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: int) sort order: + Map-reduce partition columns: key (type: int) Statistics: Num rows: 724 Data size: 2897 Basic stats: COMPLETE Column stats: NONE TableScan alias: m Statistics: Num rows: 54 Data size: 216 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 27 Data size: 108 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: int) sort order: + Map-reduce partition columns: key (type: int) Statistics: Num rows: 27 Data size: 108 Basic stats: COMPLETE Column stats: NONE TableScan alias: n Statistics: Num rows: 2 Data size: 280 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 1 Data size: 140 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: int) sort order: + Map-reduce partition columns: key (type: int) Statistics: Num rows: 1 Data size: 140 Basic stats: COMPLETE Column stats: NONE value expressions: val (type: string) Reduce Operator Tree: Demux Operator Statistics: Num rows: 1479 Data size: 6053 Basic stats: COMPLETE Column stats: NONE Join Operator condition map: Inner Join 0 to 1 keys: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Mux Operator Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator expressions: _col0 (type: int), _col3 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE File Output Operator compressed: false Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest_co2 Join Operator condition map: Inner Join 0 to 1 keys: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0, _col6 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator expressions: _col0 (type: int), _col6 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Mux Operator Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator expressions: _col0 (type: int), _col3 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE File Output Operator compressed: false Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest_co2 Stage: Stage-0 Move Operator tables: replace: true table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest_co2 Stage: Stage-2 Stats-Aggr Operator PREHOOK: query: INSERT OVERWRITE TABLE dest_co2 SELECT b.key, d.val FROM (SELECT x.key, x.val FROM T1 x JOIN T2 y ON (x.key = y.key)) b JOIN (SELECT m.key, n.val FROM T3 m JOIN T4 n ON (m.key = n.key)) d ON b.key = d.key PREHOOK: type: QUERY PREHOOK: Input: default@t1 PREHOOK: Input: default@t2 PREHOOK: Input: default@t3 PREHOOK: Input: default@t4 PREHOOK: Output: default@dest_co2 POSTHOOK: query: INSERT OVERWRITE TABLE dest_co2 SELECT b.key, d.val FROM (SELECT x.key, x.val FROM T1 x JOIN T2 y ON (x.key = y.key)) b JOIN (SELECT m.key, n.val FROM T3 m JOIN T4 n ON (m.key = n.key)) d ON b.key = d.key POSTHOOK: type: QUERY POSTHOOK: Input: default@t1 POSTHOOK: Input: default@t2 POSTHOOK: Input: default@t3 POSTHOOK: Input: default@t4 POSTHOOK: Output: default@dest_co2 POSTHOOK: Lineage: dest_co2.key EXPRESSION [(t1)x.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: dest_co2.val SIMPLE [(t4)n.FieldSchema(name:val, type:string, comment:null), ] PREHOOK: query: -- Enable hive.auto.convert.join. EXPLAIN INSERT OVERWRITE TABLE dest_co3 SELECT b.key, d.val FROM (SELECT x.key, x.val FROM T1 x JOIN T2 y ON (x.key = y.key)) b JOIN (SELECT m.key, n.val FROM T3 m JOIN T4 n ON (m.key = n.key)) d ON b.key = d.key PREHOOK: type: QUERY POSTHOOK: query: -- Enable hive.auto.convert.join. EXPLAIN INSERT OVERWRITE TABLE dest_co3 SELECT b.key, d.val FROM (SELECT x.key, x.val FROM T1 x JOIN T2 y ON (x.key = y.key)) b JOIN (SELECT m.key, n.val FROM T3 m JOIN T4 n ON (m.key = n.key)) d ON b.key = d.key POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-14 is a root stage Stage-10 depends on stages: Stage-14 Stage-9 depends on stages: Stage-10, Stage-11 , consists of Stage-12, Stage-13, Stage-2 Stage-12 has a backup stage: Stage-2 Stage-7 depends on stages: Stage-12 Stage-0 depends on stages: Stage-2, Stage-7, Stage-8 Stage-3 depends on stages: Stage-0 Stage-13 has a backup stage: Stage-2 Stage-8 depends on stages: Stage-13 Stage-2 Stage-15 is a root stage Stage-11 depends on stages: Stage-15 STAGE PLANS: Stage: Stage-14 Map Reduce Local Work Alias -> Map Local Tables: b:y Fetch Operator limit: -1 Alias -> Map Local Operator Tree: b:y TableScan alias: y Statistics: Num rows: 1447 Data size: 5791 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 724 Data size: 2897 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 key (type: int) 1 key (type: int) Stage: Stage-10 Map Reduce Map Operator Tree: TableScan alias: x Statistics: Num rows: 1453 Data size: 5812 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 727 Data size: 2908 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0 Statistics: Num rows: 799 Data size: 3198 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work Stage: Stage-9 Conditional Operator Stage: Stage-12 Map Reduce Local Work Alias -> Map Local Tables: $INTNAME1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: $INTNAME1 TableScan HashTable Sink Operator keys: 0 _col0 (type: int) 1 _col0 (type: int) Stage: Stage-7 Map Reduce Map Operator Tree: TableScan Map Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col3 Select Operator expressions: _col0 (type: int), _col3 (type: string) outputColumnNames: _col0, _col1 File Output Operator compressed: false table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest_co3 Local Work: Map Reduce Local Work Stage: Stage-0 Move Operator tables: replace: true table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest_co3 Stage: Stage-3 Stats-Aggr Operator Stage: Stage-13 Map Reduce Local Work Alias -> Map Local Tables: $INTNAME Fetch Operator limit: -1 Alias -> Map Local Operator Tree: $INTNAME TableScan HashTable Sink Operator keys: 0 _col0 (type: int) 1 _col0 (type: int) Stage: Stage-8 Map Reduce Map Operator Tree: TableScan Map Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col3 Select Operator expressions: _col0 (type: int), _col3 (type: string) outputColumnNames: _col0, _col1 File Output Operator compressed: false table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest_co3 Local Work: Map Reduce Local Work Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 799 Data size: 3198 Basic stats: COMPLETE Column stats: NONE TableScan Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 29 Data size: 118 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col3 Statistics: Num rows: 878 Data size: 3517 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col3 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 878 Data size: 3517 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Statistics: Num rows: 878 Data size: 3517 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest_co3 Stage: Stage-15 Map Reduce Local Work Alias -> Map Local Tables: d:m Fetch Operator limit: -1 Alias -> Map Local Operator Tree: d:m TableScan alias: m Statistics: Num rows: 54 Data size: 216 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 27 Data size: 108 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 key (type: int) 1 key (type: int) Stage: Stage-11 Map Reduce Map Operator Tree: TableScan alias: n Statistics: Num rows: 2 Data size: 280 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 1 Data size: 140 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0, _col6 Statistics: Num rows: 29 Data size: 118 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col6 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 29 Data size: 118 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work PREHOOK: query: INSERT OVERWRITE TABLE dest_co3 SELECT b.key, d.val FROM (SELECT x.key, x.val FROM T1 x JOIN T2 y ON (x.key = y.key)) b JOIN (SELECT m.key, n.val FROM T3 m JOIN T4 n ON (m.key = n.key)) d ON b.key = d.key PREHOOK: type: QUERY PREHOOK: Input: default@t1 PREHOOK: Input: default@t2 PREHOOK: Input: default@t3 PREHOOK: Input: default@t4 PREHOOK: Output: default@dest_co3 POSTHOOK: query: INSERT OVERWRITE TABLE dest_co3 SELECT b.key, d.val FROM (SELECT x.key, x.val FROM T1 x JOIN T2 y ON (x.key = y.key)) b JOIN (SELECT m.key, n.val FROM T3 m JOIN T4 n ON (m.key = n.key)) d ON b.key = d.key POSTHOOK: type: QUERY POSTHOOK: Input: default@t1 POSTHOOK: Input: default@t2 POSTHOOK: Input: default@t3 POSTHOOK: Input: default@t4 POSTHOOK: Output: default@dest_co3 POSTHOOK: Lineage: dest_co3.key EXPRESSION [(t1)x.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: dest_co3.val SIMPLE [(t4)n.FieldSchema(name:val, type:string, comment:null), ] PREHOOK: query: -- dest_co1, dest_co2 and dest_co3 should be same -- SELECT * FROM dest_co1 x ORDER BY x.key, x.val; -- SELECT * FROM dest_co2 x ORDER BY x.key, x.val; SELECT SUM(HASH(key)), SUM(HASH(val)) FROM dest_co1 PREHOOK: type: QUERY PREHOOK: Input: default@dest_co1 #### A masked pattern was here #### POSTHOOK: query: -- dest_co1, dest_co2 and dest_co3 should be same -- SELECT * FROM dest_co1 x ORDER BY x.key, x.val; -- SELECT * FROM dest_co2 x ORDER BY x.key, x.val; SELECT SUM(HASH(key)), SUM(HASH(val)) FROM dest_co1 POSTHOOK: type: QUERY POSTHOOK: Input: default@dest_co1 #### A masked pattern was here #### 8409 7619696771 PREHOOK: query: SELECT SUM(HASH(key)), SUM(HASH(val)) FROM dest_co2 PREHOOK: type: QUERY PREHOOK: Input: default@dest_co2 #### A masked pattern was here #### POSTHOOK: query: SELECT SUM(HASH(key)), SUM(HASH(val)) FROM dest_co2 POSTHOOK: type: QUERY POSTHOOK: Input: default@dest_co2 #### A masked pattern was here #### 8409 7619696771 PREHOOK: query: SELECT SUM(HASH(key)), SUM(HASH(val)) FROM dest_co3 PREHOOK: type: QUERY PREHOOK: Input: default@dest_co3 #### A masked pattern was here #### POSTHOOK: query: SELECT SUM(HASH(key)), SUM(HASH(val)) FROM dest_co3 POSTHOOK: type: QUERY POSTHOOK: Input: default@dest_co3 #### A masked pattern was here #### 8409 7619696771