Modified: hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer2.q.out URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer2.q.out?rev=1640577&r1=1640576&r2=1640577&view=diff ============================================================================== --- hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer2.q.out (original) +++ hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer2.q.out Wed Nov 19 15:54:15 2014 @@ -41,39 +41,31 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: key, value + Group By Operator + aggregations: count(value) + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(value) - keys: key (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 13 Data size: 99 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: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 45 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 + Statistics: Num rows: 13 Data size: 99 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 @@ -83,14 +75,14 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) TableScan Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Join Operator @@ -100,22 +92,18 @@ STAGE PLANS: 0 {KEY.reducesinkkey0} {VALUE._col0} 1 {KEY.reducesinkkey0} {VALUE._col0} outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint) + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) + mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 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 + Statistics: Num rows: 1 Data size: 32 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 @@ -152,39 +140,31 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: key, value + Group By Operator + aggregations: count(value) + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(value) - keys: key (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 250 Data size: 2656 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 125 Data size: 1328 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 + Statistics: Num rows: 250 Data size: 2656 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-0 Fetch Operator @@ -240,44 +220,36 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: key, value + Group By Operator + aggregations: count(value) + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(value) - keys: key (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 13 Data size: 99 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: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) TableScan alias: x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: key, value + Group By Operator + aggregations: count(value) + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(value) - keys: key (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 250 Data size: 2656 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Demux Operator Statistics: Num rows: 263 Data size: 2755 Basic stats: COMPLETE Column stats: NONE @@ -287,70 +259,54 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE - Mux Operator - Statistics: Num rows: 262 Data size: 2744 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 {KEY.reducesinkkey0} {VALUE._col0} + Mux Operator + Statistics: Num rows: 262 Data size: 2744 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) + mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 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 + Statistics: Num rows: 1 Data size: 32 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 Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE - Mux Operator - Statistics: Num rows: 262 Data size: 2744 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 {KEY.reducesinkkey0} {VALUE._col0} + Mux Operator + Statistics: Num rows: 262 Data size: 2744 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) + mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 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 + Statistics: Num rows: 1 Data size: 32 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 @@ -455,17 +411,13 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 91 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 + Statistics: Num rows: 25 Data size: 191 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 @@ -475,14 +427,14 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) TableScan Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Join Operator @@ -492,22 +444,18 @@ STAGE PLANS: 0 {KEY.reducesinkkey0} {VALUE._col0} 1 {KEY.reducesinkkey0} {VALUE._col0} outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint) + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) + mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 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 + Statistics: Num rows: 1 Data size: 32 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 @@ -563,17 +511,13 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 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 + Statistics: Num rows: 500 Data size: 5312 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-0 Fetch Operator @@ -670,70 +614,54 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE - Mux Operator - Statistics: Num rows: 524 Data size: 5492 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Left Outer Join0 to 1 - condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 {KEY.reducesinkkey0} {VALUE._col0} + Mux Operator + Statistics: Num rows: 524 Data size: 5492 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Left Outer Join0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) + mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 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 + Statistics: Num rows: 1 Data size: 32 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 Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE - Mux Operator - Statistics: Num rows: 524 Data size: 5492 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Left Outer Join0 to 1 - condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 {KEY.reducesinkkey0} {VALUE._col0} + Mux Operator + Statistics: Num rows: 524 Data size: 5492 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Left Outer Join0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) + mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 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 + Statistics: Num rows: 1 Data size: 32 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 @@ -838,17 +766,13 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 91 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 + Statistics: Num rows: 25 Data size: 191 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 @@ -858,14 +782,14 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) TableScan Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Join Operator @@ -875,22 +799,18 @@ STAGE PLANS: 0 {KEY.reducesinkkey0} {VALUE._col0} 1 {KEY.reducesinkkey0} {VALUE._col0} outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint) + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) + mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 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 + Statistics: Num rows: 1 Data size: 32 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 @@ -946,17 +866,13 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 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 + Statistics: Num rows: 500 Data size: 5312 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-0 Fetch Operator @@ -1053,70 +969,54 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE - Mux Operator - Statistics: Num rows: 524 Data size: 5492 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Right Outer Join0 to 1 - condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 {KEY.reducesinkkey0} {VALUE._col0} + Mux Operator + Statistics: Num rows: 524 Data size: 5492 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Right Outer Join0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) + mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 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 + Statistics: Num rows: 1 Data size: 32 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 Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE - Mux Operator - Statistics: Num rows: 524 Data size: 5492 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Right Outer Join0 to 1 - condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 {KEY.reducesinkkey0} {VALUE._col0} + Mux Operator + Statistics: Num rows: 524 Data size: 5492 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Right Outer Join0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) + mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 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 + Statistics: Num rows: 1 Data size: 32 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 @@ -1221,17 +1121,13 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 91 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 + Statistics: Num rows: 25 Data size: 191 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 @@ -1241,14 +1137,14 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) TableScan Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Join Operator @@ -1258,22 +1154,18 @@ STAGE PLANS: 0 {KEY.reducesinkkey0} {VALUE._col0} 1 {KEY.reducesinkkey0} {VALUE._col0} outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint) + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) + mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 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 + Statistics: Num rows: 1 Data size: 32 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 @@ -1329,17 +1221,13 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 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 + Statistics: Num rows: 500 Data size: 5312 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-0 Fetch Operator @@ -1436,70 +1324,54 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE - Mux Operator - Statistics: Num rows: 524 Data size: 5492 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Outer Join 0 to 1 - condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 {KEY.reducesinkkey0} {VALUE._col0} + Mux Operator + Statistics: Num rows: 524 Data size: 5492 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Outer Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) + mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 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 + Statistics: Num rows: 1 Data size: 32 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 Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE - Mux Operator - Statistics: Num rows: 524 Data size: 5492 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Outer Join 0 to 1 - condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 {KEY.reducesinkkey0} {VALUE._col0} + Mux Operator + Statistics: Num rows: 524 Data size: 5492 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Outer Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) + mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 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 + Statistics: Num rows: 1 Data size: 32 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 @@ -1641,22 +1513,18 @@ STAGE PLANS: 1 outputColumnNames: _col0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count(1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 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 + 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 @@ -1675,21 +1543,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + Group By Operator + aggregations: sum(hash(_col0)), sum(hash(_col1)) + mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 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 + Statistics: Num rows: 1 Data size: 16 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-4 Map Reduce @@ -1877,22 +1741,18 @@ STAGE PLANS: 1 outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count(1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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 + 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 Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) @@ -1913,22 +1773,18 @@ STAGE PLANS: 1 outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count(1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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 + 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 @@ -1947,21 +1803,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + Group By Operator + aggregations: sum(hash(_col0)), sum(hash(_col1)) + mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 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 + Statistics: Num rows: 1 Data size: 16 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 @@ -2055,39 +1907,31 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: key, value + Group By Operator + aggregations: count(value) + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(value) - keys: key (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 13 Data size: 99 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: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 45 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 + Statistics: Num rows: 13 Data size: 99 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 @@ -2097,7 +1941,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) TableScan Reduce Output Operator @@ -2115,21 +1959,17 @@ STAGE PLANS: 1 {KEY.reducesinkkey0} {VALUE._col0} outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: bigint) + Group By Operator + aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) + mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 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 + Statistics: Num rows: 1 Data size: 32 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 @@ -2192,16 +2032,12 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 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 + 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-0 Fetch Operator @@ -2257,22 +2093,18 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: key, value + Group By Operator + aggregations: count(value) + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(value) - keys: key (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 13 Data size: 99 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: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) TableScan alias: x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -2307,70 +2139,54 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Mux Operator - Statistics: Num rows: 138 Data size: 1427 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 {KEY.reducesinkkey0} {VALUE._col0} + Mux Operator + Statistics: Num rows: 138 Data size: 1427 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) + mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: bigint) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 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 + Statistics: Num rows: 1 Data size: 32 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 Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 138 Data size: 1427 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) - outputColumnNames: _col0, _col1 + Mux Operator Statistics: Num rows: 138 Data size: 1427 Basic stats: COMPLETE Column stats: NONE - Mux Operator - Statistics: Num rows: 138 Data size: 1427 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 {KEY.reducesinkkey0} {VALUE._col0} + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) + mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: bigint) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 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 + Statistics: Num rows: 1 Data size: 32 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
