PREHOOK: query: -- SORT_QUERY_RESULTS DROP TABLE part PREHOOK: type: DROPTABLE POSTHOOK: query: -- SORT_QUERY_RESULTS DROP TABLE part POSTHOOK: type: DROPTABLE PREHOOK: query: -- data setup CREATE TABLE part( p_partkey INT, p_name STRING, p_mfgr STRING, p_brand STRING, p_type STRING, p_size INT, p_container STRING, p_retailprice DOUBLE, p_comment STRING ) PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@part POSTHOOK: query: -- data setup CREATE TABLE part( p_partkey INT, p_name STRING, p_mfgr STRING, p_brand STRING, p_type STRING, p_size INT, p_container STRING, p_retailprice DOUBLE, p_comment STRING ) POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@part PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/part_tiny.txt' overwrite into table part PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@part POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/part_tiny.txt' overwrite into table part POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@part PREHOOK: query: DROP TABLE lineitem PREHOOK: type: DROPTABLE POSTHOOK: query: DROP TABLE lineitem POSTHOOK: type: DROPTABLE PREHOOK: query: CREATE TABLE lineitem (L_ORDERKEY INT, L_PARTKEY INT, L_SUPPKEY INT, L_LINENUMBER INT, L_QUANTITY DOUBLE, L_EXTENDEDPRICE DOUBLE, L_DISCOUNT DOUBLE, L_TAX DOUBLE, L_RETURNFLAG STRING, L_LINESTATUS STRING, l_shipdate STRING, L_COMMITDATE STRING, L_RECEIPTDATE STRING, L_SHIPINSTRUCT STRING, L_SHIPMODE STRING, L_COMMENT STRING) ROW FORMAT DELIMITED FIELDS TERMINATED BY '|' PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@lineitem POSTHOOK: query: CREATE TABLE lineitem (L_ORDERKEY INT, L_PARTKEY INT, L_SUPPKEY INT, L_LINENUMBER INT, L_QUANTITY DOUBLE, L_EXTENDEDPRICE DOUBLE, L_DISCOUNT DOUBLE, L_TAX DOUBLE, L_RETURNFLAG STRING, L_LINESTATUS STRING, l_shipdate STRING, L_COMMITDATE STRING, L_RECEIPTDATE STRING, L_SHIPINSTRUCT STRING, L_SHIPMODE STRING, L_COMMENT STRING) ROW FORMAT DELIMITED FIELDS TERMINATED BY '|' POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@lineitem PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/lineitem.txt' OVERWRITE INTO TABLE lineitem PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@lineitem POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/lineitem.txt' OVERWRITE INTO TABLE lineitem POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@lineitem PREHOOK: query: -- non agg, non corr explain select * from src where src.key in (select key from src s1 where s1.key > '9') PREHOOK: type: QUERY POSTHOOK: query: -- non agg, non corr explain select * from src where src.key in (select key from src s1 where s1.key > '9') POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: s1 Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key > '9') and key is not null) (type: boolean) Statistics: Num rows: 10 Data size: 1002 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 Statistics: Num rows: 10 Data size: 1002 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 10 Data size: 1002 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 10 Data size: 1002 Basic stats: COMPLETE Column stats: NONE TableScan alias: src Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 15 Data size: 3006 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) Statistics: Num rows: 15 Data size: 3006 Basic stats: COMPLETE Column stats: NONE value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Left Semi Join 0 to 1 condition expressions: 0 {KEY.reducesinkkey0} {VALUE._col0} 1 outputColumnNames: _col0, _col1 Statistics: Num rows: 16 Data size: 3306 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 16 Data size: 3306 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Statistics: Num rows: 16 Data size: 3306 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: ListSink PREHOOK: query: select * from src where src.key in (select key from src s1 where s1.key > '9') PREHOOK: type: QUERY PREHOOK: Input: default@src #### A masked pattern was here #### POSTHOOK: query: select * from src where src.key in (select key from src s1 where s1.key > '9') POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### 90 val_90 90 val_90 90 val_90 92 val_92 95 val_95 95 val_95 96 val_96 97 val_97 97 val_97 98 val_98 98 val_98 PREHOOK: query: -- non agg, corr explain select * from src b where b.key in (select a.key from src a where b.value = a.value and a.key > '9' ) PREHOOK: type: QUERY POSTHOOK: query: -- non agg, corr explain select * from src b where b.key in (select a.key from src a where b.value = a.value and a.key > '9' ) POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: b Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key is not null and value is not null) (type: boolean) Statistics: Num rows: 8 Data size: 1603 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string), value (type: string) Statistics: Num rows: 8 Data size: 1603 Basic stats: COMPLETE Column stats: NONE TableScan alias: a Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key > '9') and key is not null) and value is not null) (type: boolean) Statistics: Num rows: 3 Data size: 601 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 601 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 601 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 3 Data size: 601 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Semi Join 0 to 1 condition expressions: 0 {KEY.reducesinkkey0} {KEY.reducesinkkey1} 1 outputColumnNames: _col0, _col1 Statistics: Num rows: 8 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 8 Data size: 1763 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Statistics: Num rows: 8 Data size: 1763 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: ListSink PREHOOK: query: select * from src b where b.key in (select a.key from src a where b.value = a.value and a.key > '9' ) PREHOOK: type: QUERY PREHOOK: Input: default@src #### A masked pattern was here #### POSTHOOK: query: select * from src b where b.key in (select a.key from src a where b.value = a.value and a.key > '9' ) POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### 90 val_90 90 val_90 90 val_90 92 val_92 95 val_95 95 val_95 96 val_96 97 val_97 97 val_97 98 val_98 98 val_98 PREHOOK: query: -- agg, non corr explain select p_name, p_size from part where part.p_size in (select avg(p_size) from (select p_size, rank() over(partition by p_mfgr order by p_size) as r from part) a where r <= 2 ) PREHOOK: type: QUERY POSTHOOK: query: -- agg, non corr explain select p_name, p_size from part where part.p_size in (select avg(p_size) from (select p_size, rank() over(partition by p_mfgr order by p_size) as r from part) a where r <= 2 ) POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 Stage-3 depends on stages: Stage-2 Stage-0 depends on stages: Stage-3 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: part Statistics: Num rows: 30 Data size: 3173 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: p_mfgr (type: string), p_size (type: int) sort order: ++ Map-reduce partition columns: p_mfgr (type: string) Statistics: Num rows: 30 Data size: 3173 Basic stats: COMPLETE Column stats: NONE value expressions: p_mfgr (type: string), p_size (type: int) Reduce Operator Tree: Extract Statistics: Num rows: 30 Data size: 3173 Basic stats: COMPLETE Column stats: NONE PTF Operator Statistics: Num rows: 30 Data size: 3173 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (_wcol0 <= 2) (type: boolean) Statistics: Num rows: 10 Data size: 1057 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col5 (type: int) outputColumnNames: _col0 Statistics: Num rows: 10 Data size: 1057 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: avg(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL 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 sort order: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col0 (type: struct) Reduce Operator Tree: Group By Operator aggregations: avg(VALUE._col0) mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: _col0 is not null (type: boolean) Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: double) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: double) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 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-3 Map Reduce Map Operator Tree: TableScan Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE TableScan alias: part Statistics: Num rows: 30 Data size: 3173 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: UDFToDouble(p_size) is not null (type: boolean) Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: UDFToDouble(p_size) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(p_size) (type: double) Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE value expressions: p_name (type: string), p_size (type: int) Reduce Operator Tree: Join Operator condition map: Left Semi Join 0 to 1 condition expressions: 0 {VALUE._col1} {VALUE._col5} 1 outputColumnNames: _col1, _col5 Statistics: Num rows: 16 Data size: 1744 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: string), _col5 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 16 Data size: 1744 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Statistics: Num rows: 16 Data size: 1744 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: ListSink PREHOOK: query: select p_name, p_size from part where part.p_size in (select avg(p_size) from (select p_size, rank() over(partition by p_mfgr order by p_size) as r from part) a where r <= 2 ) PREHOOK: type: QUERY PREHOOK: Input: default@part #### A masked pattern was here #### POSTHOOK: query: select p_name, p_size from part where part.p_size in (select avg(p_size) from (select p_size, rank() over(partition by p_mfgr order by p_size) as r from part) a where r <= 2 ) POSTHOOK: type: QUERY POSTHOOK: Input: default@part #### A masked pattern was here #### almond antique medium spring khaki 6 almond antique salmon chartreuse burlywood 6 PREHOOK: query: -- agg, corr explain select p_mfgr, p_name, p_size from part b where b.p_size in (select min(p_size) from (select p_mfgr, p_size, rank() over(partition by p_mfgr order by p_size) as r from part) a where r <= 2 and b.p_mfgr = a.p_mfgr ) PREHOOK: type: QUERY POSTHOOK: query: -- agg, corr explain select p_mfgr, p_name, p_size from part b where b.p_size in (select min(p_size) from (select p_mfgr, p_size, rank() over(partition by p_mfgr order by p_size) as r from part) a where r <= 2 and b.p_mfgr = a.p_mfgr ) POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-2 is a root stage Stage-3 depends on stages: Stage-2 Stage-1 depends on stages: Stage-3 Stage-0 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-2 Map Reduce Map Operator Tree: TableScan alias: part Statistics: Num rows: 30 Data size: 3173 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: p_mfgr (type: string), p_size (type: int) sort order: ++ Map-reduce partition columns: p_mfgr (type: string) Statistics: Num rows: 30 Data size: 3173 Basic stats: COMPLETE Column stats: NONE value expressions: p_mfgr (type: string), p_size (type: int) Reduce Operator Tree: Extract Statistics: Num rows: 30 Data size: 3173 Basic stats: COMPLETE Column stats: NONE PTF Operator Statistics: Num rows: 30 Data size: 3173 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((_wcol0 <= 2) and _col2 is not null) (type: boolean) Statistics: Num rows: 5 Data size: 528 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: string), _col5 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 5 Data size: 528 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: min(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 5 Data size: 528 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-3 Map Reduce Map Operator Tree: TableScan Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 5 Data size: 528 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int) Reduce Operator Tree: Group By Operator aggregations: min(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 2 Data size: 211 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: _col1 is not null (type: boolean) Statistics: Num rows: 2 Data size: 211 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: int), _col0 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 2 Data size: 211 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: int), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 2 Data size: 211 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-1 Map Reduce Map Operator Tree: TableScan alias: b Statistics: Num rows: 15 Data size: 3173 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (p_size is not null and p_mfgr is not null) (type: boolean) Statistics: Num rows: 4 Data size: 846 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: p_size (type: int), p_mfgr (type: string) sort order: ++ Map-reduce partition columns: p_size (type: int), p_mfgr (type: string) Statistics: Num rows: 4 Data size: 846 Basic stats: COMPLETE Column stats: NONE value expressions: p_name (type: string) TableScan Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) Statistics: Num rows: 2 Data size: 211 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Semi Join 0 to 1 condition expressions: 0 {VALUE._col1} {KEY.reducesinkkey1} {KEY.reducesinkkey0} 1 outputColumnNames: _col1, _col2, _col5 Statistics: Num rows: 4 Data size: 930 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 4 Data size: 930 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Statistics: Num rows: 4 Data size: 930 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: ListSink PREHOOK: query: select p_mfgr, p_name, p_size from part b where b.p_size in (select min(p_size) from (select p_mfgr, p_size, rank() over(partition by p_mfgr order by p_size) as r from part) a where r <= 2 and b.p_mfgr = a.p_mfgr ) PREHOOK: type: QUERY PREHOOK: Input: default@part #### A masked pattern was here #### POSTHOOK: query: select p_mfgr, p_name, p_size from part b where b.p_size in (select min(p_size) from (select p_mfgr, p_size, rank() over(partition by p_mfgr order by p_size) as r from part) a where r <= 2 and b.p_mfgr = a.p_mfgr ) POSTHOOK: type: QUERY POSTHOOK: Input: default@part #### A masked pattern was here #### Manufacturer#1 almond antique burnished rose metallic 2 Manufacturer#1 almond antique burnished rose metallic 2 Manufacturer#2 almond aquamarine midnight light salmon 2 Manufacturer#3 almond antique misty red olive 1 Manufacturer#4 almond aquamarine yellow dodger mint 7 Manufacturer#5 almond antique sky peru orange 2 PREHOOK: query: -- distinct, corr explain select * from src b where b.key in (select distinct a.key from src a where b.value = a.value and a.key > '9' ) PREHOOK: type: QUERY POSTHOOK: query: -- distinct, corr explain select * from src b where b.key in (select distinct a.key from src a where b.value = a.value and a.key > '9' ) POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-2 is a root stage Stage-1 depends on stages: Stage-2 Stage-0 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-2 Map Reduce Map Operator Tree: TableScan alias: a Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key > '9') and key is not null) and value is not null) (type: boolean) Statistics: Num rows: 3 Data size: 601 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value Statistics: Num rows: 3 Data size: 601 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 601 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 3 Data size: 601 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 200 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-1 Map Reduce Map Operator Tree: TableScan alias: b Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key is not null and value is not null) (type: boolean) Statistics: Num rows: 8 Data size: 1603 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string), value (type: string) Statistics: Num rows: 8 Data size: 1603 Basic stats: COMPLETE Column stats: NONE TableScan Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Semi Join 0 to 1 condition expressions: 0 {KEY.reducesinkkey0} {KEY.reducesinkkey1} 1 outputColumnNames: _col0, _col1 Statistics: Num rows: 8 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 8 Data size: 1763 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Statistics: Num rows: 8 Data size: 1763 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: ListSink PREHOOK: query: select * from src b where b.key in (select distinct a.key from src a where b.value = a.value and a.key > '9' ) PREHOOK: type: QUERY PREHOOK: Input: default@src #### A masked pattern was here #### POSTHOOK: query: select * from src b where b.key in (select distinct a.key from src a where b.value = a.value and a.key > '9' ) POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### 90 val_90 90 val_90 90 val_90 92 val_92 95 val_95 95 val_95 96 val_96 97 val_97 97 val_97 98 val_98 98 val_98 PREHOOK: query: -- non agg, non corr, windowing select p_mfgr, p_name, p_size from part where part.p_size in (select first_value(p_size) over(partition by p_mfgr order by p_size) from part) PREHOOK: type: QUERY PREHOOK: Input: default@part #### A masked pattern was here #### POSTHOOK: query: -- non agg, non corr, windowing select p_mfgr, p_name, p_size from part where part.p_size in (select first_value(p_size) over(partition by p_mfgr order by p_size) from part) POSTHOOK: type: QUERY POSTHOOK: Input: default@part #### A masked pattern was here #### Manufacturer#1 almond antique burnished rose metallic 2 Manufacturer#1 almond antique burnished rose metallic 2 Manufacturer#2 almond aquamarine midnight light salmon 2 Manufacturer#3 almond antique misty red olive 1 Manufacturer#4 almond aquamarine yellow dodger mint 7 Manufacturer#5 almond antique sky peru orange 2 PREHOOK: query: -- non agg, non corr, with join in Parent Query explain select p.p_partkey, li.l_suppkey from (select distinct l_partkey as p_partkey from lineitem) p join lineitem li on p.p_partkey = li.l_partkey where li.l_linenumber = 1 and li.l_orderkey in (select l_orderkey from lineitem where l_shipmode = 'AIR') PREHOOK: type: QUERY POSTHOOK: query: -- non agg, non corr, with join in Parent Query explain select p.p_partkey, li.l_suppkey from (select distinct l_partkey as p_partkey from lineitem) p join lineitem li on p.p_partkey = li.l_partkey where li.l_linenumber = 1 and li.l_orderkey in (select l_orderkey from lineitem where l_shipmode = 'AIR') POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-3 is a root stage Stage-1 depends on stages: Stage-3 Stage-2 depends on stages: Stage-1 Stage-0 depends on stages: Stage-2 STAGE PLANS: Stage: Stage-3 Map Reduce Map Operator Tree: TableScan alias: lineitem Statistics: Num rows: 3024 Data size: 12099 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: l_partkey is not null (type: boolean) Statistics: Num rows: 1512 Data size: 6049 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_partkey (type: int) outputColumnNames: l_partkey Statistics: Num rows: 1512 Data size: 6049 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: l_partkey (type: int) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1512 Data size: 6049 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 1512 Data size: 6049 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 756 Data size: 3024 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int) outputColumnNames: _col0 Statistics: Num rows: 756 Data size: 3024 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-1 Map Reduce Map Operator Tree: TableScan alias: li Statistics: Num rows: 756 Data size: 12099 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((l_partkey is not null and l_orderkey is not null) and (l_linenumber = 1)) (type: boolean) Statistics: Num rows: 94 Data size: 1504 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: l_partkey (type: int) sort order: + Map-reduce partition columns: l_partkey (type: int) Statistics: Num rows: 94 Data size: 1504 Basic stats: COMPLETE Column stats: NONE value expressions: l_orderkey (type: int), l_suppkey (type: int) TableScan Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 756 Data size: 3024 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 condition expressions: 0 {KEY.reducesinkkey0} 1 {VALUE._col0} {VALUE._col1} outputColumnNames: _col0, _col1, _col3 Statistics: Num rows: 831 Data size: 3326 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: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) Statistics: Num rows: 831 Data size: 3326 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col3 (type: int) TableScan alias: lineitem Statistics: Num rows: 1728 Data size: 12099 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((l_shipmode = 'AIR') and l_orderkey is not null) (type: boolean) Statistics: Num rows: 432 Data size: 3024 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_orderkey (type: int) outputColumnNames: _col0 Statistics: Num rows: 432 Data size: 3024 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: int) mode: hash outputColumnNames: _col0 Statistics: Num rows: 432 Data size: 3024 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 432 Data size: 3024 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Semi Join 0 to 1 condition expressions: 0 {VALUE._col0} {VALUE._col2} 1 outputColumnNames: _col0, _col3 Statistics: Num rows: 914 Data size: 3658 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col3 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 914 Data size: 3658 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Statistics: Num rows: 914 Data size: 3658 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: ListSink PREHOOK: query: select p.p_partkey, li.l_suppkey from (select distinct l_partkey as p_partkey from lineitem) p join lineitem li on p.p_partkey = li.l_partkey where li.l_linenumber = 1 and li.l_orderkey in (select l_orderkey from lineitem where l_shipmode = 'AIR') PREHOOK: type: QUERY PREHOOK: Input: default@lineitem #### A masked pattern was here #### POSTHOOK: query: select p.p_partkey, li.l_suppkey from (select distinct l_partkey as p_partkey from lineitem) p join lineitem li on p.p_partkey = li.l_partkey where li.l_linenumber = 1 and li.l_orderkey in (select l_orderkey from lineitem where l_shipmode = 'AIR') POSTHOOK: type: QUERY POSTHOOK: Input: default@lineitem #### A masked pattern was here #### 108570 8571 115118 7630 115209 7721 155190 7706 2320 9821 40216 217 4297 1798 61336 8855 64128 9141 82704 7721 PREHOOK: query: -- non agg, corr, with join in Parent Query select p.p_partkey, li.l_suppkey from (select distinct l_partkey as p_partkey from lineitem) p join lineitem li on p.p_partkey = li.l_partkey where li.l_linenumber = 1 and li.l_orderkey in (select l_orderkey from lineitem where l_shipmode = 'AIR' and l_linenumber = li.l_linenumber) PREHOOK: type: QUERY PREHOOK: Input: default@lineitem #### A masked pattern was here #### POSTHOOK: query: -- non agg, corr, with join in Parent Query select p.p_partkey, li.l_suppkey from (select distinct l_partkey as p_partkey from lineitem) p join lineitem li on p.p_partkey = li.l_partkey where li.l_linenumber = 1 and li.l_orderkey in (select l_orderkey from lineitem where l_shipmode = 'AIR' and l_linenumber = li.l_linenumber) POSTHOOK: type: QUERY POSTHOOK: Input: default@lineitem #### A masked pattern was here #### 108570 8571 4297 1798