http://git-wip-us.apache.org/repos/asf/hive/blob/b650083f/ql/src/test/results/clientpositive/merge4.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/merge4.q.out b/ql/src/test/results/clientpositive/merge4.q.out index fcc557a..621601d 100644 --- a/ql/src/test/results/clientpositive/merge4.q.out +++ b/ql/src/test/results/clientpositive/merge4.q.out @@ -21,13 +21,14 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 - Stage-4 - Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 - Stage-2 depends on stages: Stage-0 - Stage-3 + Stage-2 depends on stages: Stage-1 + Stage-8 depends on stages: Stage-2 , consists of Stage-5, Stage-4, Stage-6 Stage-5 - Stage-6 depends on stages: Stage-5 + Stage-0 depends on stages: Stage-5, Stage-4, Stage-7 + Stage-3 depends on stages: Stage-0 + Stage-4 + Stage-6 + Stage-7 depends on stages: Stage-6 STAGE PLANS: Stage: Stage-1 @@ -41,11 +42,56 @@ STAGE PLANS: expressions: key (type: string), value (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: string) - sort order: + - Map-reduce partition columns: _col2 (type: string) - value expressions: _col0 (type: string), _col1 (type: string) + Select Operator + expressions: _col0 (type: string), _col1 (type: string), '2010-08-15' (type: string), _col2 (type: string) + outputColumnNames: key, value, ds, hr + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string), hr (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1000 Data size: 10624 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: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + 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 + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-2 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + key expressions: _col2 (type: string) + sort order: + + Map-reduce partition columns: _col2 (type: string) + value expressions: _col0 (type: string), _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator @@ -61,10 +107,10 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.nzhang_part - Stage: Stage-7 + Stage: Stage-8 Conditional Operator - Stage: Stage-4 + Stage: Stage-5 Move Operator files: hdfs directory: true @@ -83,7 +129,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.nzhang_part - Stage: Stage-2 + Stage: Stage-3 Stats Work Basic Stats Work: Column Stats Desc: @@ -91,7 +137,7 @@ STAGE PLANS: Column Types: string, string Table: default.nzhang_part - Stage: Stage-3 + Stage: Stage-4 Map Reduce Map Operator Tree: TableScan @@ -103,7 +149,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.nzhang_part - Stage: Stage-5 + Stage: Stage-6 Map Reduce Map Operator Tree: TableScan @@ -115,7 +161,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.nzhang_part - Stage: Stage-6 + Stage: Stage-7 Move Operator files: hdfs directory: true
http://git-wip-us.apache.org/repos/asf/hive/blob/b650083f/ql/src/test/results/clientpositive/merge_dynamic_partition.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/merge_dynamic_partition.q.out b/ql/src/test/results/clientpositive/merge_dynamic_partition.q.out index 6e75c6e..c17d2c3 100644 --- a/ql/src/test/results/clientpositive/merge_dynamic_partition.q.out +++ b/ql/src/test/results/clientpositive/merge_dynamic_partition.q.out @@ -60,8 +60,9 @@ POSTHOOK: Input: default@srcpart_merge_dp_n1 POSTHOOK: Input: default@srcpart_merge_dp_n1@ds=2008-04-08/hr=11 STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - Stage-2 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-1 @@ -75,11 +76,56 @@ STAGE PLANS: expressions: key (type: string), value (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 99 Data size: 58120 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: string) - sort order: + - Map-reduce partition columns: _col2 (type: string) - value expressions: _col0 (type: string), _col1 (type: string) + Select Operator + expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), _col2 (type: string) + outputColumnNames: key, value, ds, hr + Statistics: Num rows: 99 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string), hr (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 99 Data size: 58120 Basic stats: PARTIAL 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: 99 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + value expressions: _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + 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 + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 49 Data size: 28766 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 49 Data size: 28766 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 49 Data size: 28766 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-2 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + key expressions: _col2 (type: string) + sort order: + + Map-reduce partition columns: _col2 (type: string) + value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY._col2 (type: string) @@ -107,7 +153,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.merge_dynamic_part_n1 - Stage: Stage-2 + Stage: Stage-3 Stats Work Basic Stats Work: Column Stats Desc: @@ -1343,13 +1389,14 @@ POSTHOOK: Input: default@srcpart_merge_dp_n1 POSTHOOK: Input: default@srcpart_merge_dp_n1@ds=2008-04-08/hr=11 STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 - Stage-4 - Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 - Stage-2 depends on stages: Stage-0 - Stage-3 + Stage-2 depends on stages: Stage-1 + Stage-8 depends on stages: Stage-2 , consists of Stage-5, Stage-4, Stage-6 Stage-5 - Stage-6 depends on stages: Stage-5 + Stage-0 depends on stages: Stage-5, Stage-4, Stage-7 + Stage-3 depends on stages: Stage-0 + Stage-4 + Stage-6 + Stage-7 depends on stages: Stage-6 STAGE PLANS: Stage: Stage-1 @@ -1363,11 +1410,56 @@ STAGE PLANS: expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 99 Data size: 58120 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: string), _col3 (type: string) - sort order: ++ - Map-reduce partition columns: _col2 (type: string), _col3 (type: string) - value expressions: _col0 (type: string), _col1 (type: string) + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + outputColumnNames: key, value, ds, hr + Statistics: Num rows: 99 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string), hr (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 99 Data size: 58120 Basic stats: PARTIAL 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: 99 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + value expressions: _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + 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 + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 49 Data size: 28766 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 49 Data size: 28766 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 49 Data size: 28766 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-2 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + key expressions: _col2 (type: string), _col3 (type: string) + sort order: ++ + Map-reduce partition columns: _col2 (type: string), _col3 (type: string) + value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string) @@ -1382,10 +1474,10 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.merge_dynamic_part_n1 - Stage: Stage-7 + Stage: Stage-8 Conditional Operator - Stage: Stage-4 + Stage: Stage-5 Move Operator files: hdfs directory: true @@ -1404,7 +1496,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.merge_dynamic_part_n1 - Stage: Stage-2 + Stage: Stage-3 Stats Work Basic Stats Work: Column Stats Desc: @@ -1412,7 +1504,7 @@ STAGE PLANS: Column Types: string, string Table: default.merge_dynamic_part_n1 - Stage: Stage-3 + Stage: Stage-4 Map Reduce Map Operator Tree: TableScan @@ -1424,7 +1516,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.merge_dynamic_part_n1 - Stage: Stage-5 + Stage: Stage-6 Map Reduce Map Operator Tree: TableScan @@ -1436,7 +1528,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.merge_dynamic_part_n1 - Stage: Stage-6 + Stage: Stage-7 Move Operator files: hdfs directory: true http://git-wip-us.apache.org/repos/asf/hive/blob/b650083f/ql/src/test/results/clientpositive/merge_dynamic_partition2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/merge_dynamic_partition2.q.out b/ql/src/test/results/clientpositive/merge_dynamic_partition2.q.out index a98bfbf..4e85457 100644 --- a/ql/src/test/results/clientpositive/merge_dynamic_partition2.q.out +++ b/ql/src/test/results/clientpositive/merge_dynamic_partition2.q.out @@ -79,13 +79,14 @@ POSTHOOK: Input: default@srcpart_merge_dp_n0@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart_merge_dp_n0@ds=2008-04-08/hr=12 STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 - Stage-4 - Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 - Stage-2 depends on stages: Stage-0 - Stage-3 + Stage-2 depends on stages: Stage-1 + Stage-8 depends on stages: Stage-2 , consists of Stage-5, Stage-4, Stage-6 Stage-5 - Stage-6 depends on stages: Stage-5 + Stage-0 depends on stages: Stage-5, Stage-4, Stage-7 + Stage-3 depends on stages: Stage-0 + Stage-4 + Stage-6 + Stage-7 depends on stages: Stage-6 STAGE PLANS: Stage: Stage-1 @@ -99,11 +100,56 @@ STAGE PLANS: expressions: key (type: string), value (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 297 Data size: 174150 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: string) - sort order: + - Map-reduce partition columns: _col2 (type: string) - value expressions: _col0 (type: string), _col1 (type: string) + Select Operator + expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), _col2 (type: string) + outputColumnNames: key, value, ds, hr + Statistics: Num rows: 297 Data size: 174150 Basic stats: PARTIAL Column stats: NONE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string), hr (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 297 Data size: 174150 Basic stats: PARTIAL 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: 297 Data size: 174150 Basic stats: PARTIAL Column stats: NONE + value expressions: _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + 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 + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 148 Data size: 86781 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 148 Data size: 86781 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 148 Data size: 86781 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-2 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + key expressions: _col2 (type: string) + sort order: + + Map-reduce partition columns: _col2 (type: string) + value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY._col2 (type: string) @@ -118,10 +164,10 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.merge_dynamic_part_n0 - Stage: Stage-7 + Stage: Stage-8 Conditional Operator - Stage: Stage-4 + Stage: Stage-5 Move Operator files: hdfs directory: true @@ -140,7 +186,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.merge_dynamic_part_n0 - Stage: Stage-2 + Stage: Stage-3 Stats Work Basic Stats Work: Column Stats Desc: @@ -148,7 +194,7 @@ STAGE PLANS: Column Types: string, string Table: default.merge_dynamic_part_n0 - Stage: Stage-3 + Stage: Stage-4 Map Reduce Map Operator Tree: TableScan @@ -160,7 +206,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.merge_dynamic_part_n0 - Stage: Stage-5 + Stage: Stage-6 Map Reduce Map Operator Tree: TableScan @@ -172,7 +218,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.merge_dynamic_part_n0 - Stage: Stage-6 + Stage: Stage-7 Move Operator files: hdfs directory: true http://git-wip-us.apache.org/repos/asf/hive/blob/b650083f/ql/src/test/results/clientpositive/merge_dynamic_partition3.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/merge_dynamic_partition3.q.out b/ql/src/test/results/clientpositive/merge_dynamic_partition3.q.out index cbc8afd..be25dd8 100644 --- a/ql/src/test/results/clientpositive/merge_dynamic_partition3.q.out +++ b/ql/src/test/results/clientpositive/merge_dynamic_partition3.q.out @@ -143,13 +143,14 @@ POSTHOOK: Input: default@srcpart_merge_dp_n2@ds=2008-04-09/hr=11 POSTHOOK: Input: default@srcpart_merge_dp_n2@ds=2008-04-09/hr=12 STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 - Stage-4 - Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 - Stage-2 depends on stages: Stage-0 - Stage-3 + Stage-2 depends on stages: Stage-1 + Stage-8 depends on stages: Stage-2 , consists of Stage-5, Stage-4, Stage-6 Stage-5 - Stage-6 depends on stages: Stage-5 + Stage-0 depends on stages: Stage-5, Stage-4, Stage-7 + Stage-3 depends on stages: Stage-0 + Stage-4 + Stage-6 + Stage-7 depends on stages: Stage-6 STAGE PLANS: Stage: Stage-1 @@ -163,11 +164,56 @@ STAGE PLANS: expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 594 Data size: 348300 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: string), _col3 (type: string) - sort order: ++ - Map-reduce partition columns: _col2 (type: string), _col3 (type: string) - value expressions: _col0 (type: string), _col1 (type: string) + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + outputColumnNames: key, value, ds, hr + Statistics: Num rows: 594 Data size: 348300 Basic stats: PARTIAL Column stats: NONE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string), hr (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 594 Data size: 348300 Basic stats: PARTIAL 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: 594 Data size: 348300 Basic stats: PARTIAL Column stats: NONE + value expressions: _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + 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 + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 297 Data size: 174150 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 297 Data size: 174150 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 297 Data size: 174150 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-2 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + key expressions: _col2 (type: string), _col3 (type: string) + sort order: ++ + Map-reduce partition columns: _col2 (type: string), _col3 (type: string) + value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string) @@ -182,10 +228,10 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.merge_dynamic_part_n2 - Stage: Stage-7 + Stage: Stage-8 Conditional Operator - Stage: Stage-4 + Stage: Stage-5 Move Operator files: hdfs directory: true @@ -204,7 +250,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.merge_dynamic_part_n2 - Stage: Stage-2 + Stage: Stage-3 Stats Work Basic Stats Work: Column Stats Desc: @@ -212,7 +258,7 @@ STAGE PLANS: Column Types: string, string Table: default.merge_dynamic_part_n2 - Stage: Stage-3 + Stage: Stage-4 Map Reduce Map Operator Tree: TableScan @@ -224,7 +270,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.merge_dynamic_part_n2 - Stage: Stage-5 + Stage: Stage-6 Map Reduce Map Operator Tree: TableScan @@ -236,7 +282,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.merge_dynamic_part_n2 - Stage: Stage-6 + Stage: Stage-7 Move Operator files: hdfs directory: true http://git-wip-us.apache.org/repos/asf/hive/blob/b650083f/ql/src/test/results/clientpositive/merge_dynamic_partition4.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/merge_dynamic_partition4.q.out b/ql/src/test/results/clientpositive/merge_dynamic_partition4.q.out index 8a4b96f..29ce8f4 100644 --- a/ql/src/test/results/clientpositive/merge_dynamic_partition4.q.out +++ b/ql/src/test/results/clientpositive/merge_dynamic_partition4.q.out @@ -140,13 +140,14 @@ POSTHOOK: Input: default@srcpart_merge_dp_rc_n1@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart_merge_dp_rc_n1@ds=2008-04-08/hr=12 STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 - Stage-4 - Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 - Stage-2 depends on stages: Stage-0 - Stage-3 + Stage-2 depends on stages: Stage-1 + Stage-8 depends on stages: Stage-2 , consists of Stage-5, Stage-4, Stage-6 Stage-5 - Stage-6 depends on stages: Stage-5 + Stage-0 depends on stages: Stage-5, Stage-4, Stage-7 + Stage-3 depends on stages: Stage-0 + Stage-4 + Stage-6 + Stage-7 depends on stages: Stage-6 STAGE PLANS: Stage: Stage-1 @@ -160,11 +161,56 @@ STAGE PLANS: expressions: key (type: string), value (type: string), if(((UDFToDouble(key) % 2.0D) = 0.0D), 'a1', 'b1') (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: string) - sort order: + - Map-reduce partition columns: _col2 (type: string) - value expressions: _col0 (type: string), _col1 (type: string) + Select Operator + expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), _col2 (type: string) + outputColumnNames: key, value, ds, hr + Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string), hr (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1000 Data size: 9624 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: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + 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 + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 500 Data size: 4812 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 500 Data size: 4812 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 500 Data size: 4812 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-2 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + key expressions: _col2 (type: string) + sort order: + + Map-reduce partition columns: _col2 (type: string) + value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY._col2 (type: string) @@ -179,10 +225,10 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe name: default.merge_dynamic_part_n3 - Stage: Stage-7 + Stage: Stage-8 Conditional Operator - Stage: Stage-4 + Stage: Stage-5 Move Operator files: hdfs directory: true @@ -201,7 +247,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe name: default.merge_dynamic_part_n3 - Stage: Stage-2 + Stage: Stage-3 Stats Work Basic Stats Work: Column Stats Desc: @@ -209,21 +255,21 @@ STAGE PLANS: Column Types: string, string Table: default.merge_dynamic_part_n3 - Stage: Stage-3 + Stage: Stage-4 Merge File Operator Map Operator Tree: RCFile Merge Operator merge level: block input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat - Stage: Stage-5 + Stage: Stage-6 Merge File Operator Map Operator Tree: RCFile Merge Operator merge level: block input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat - Stage: Stage-6 + Stage: Stage-7 Move Operator files: hdfs directory: true http://git-wip-us.apache.org/repos/asf/hive/blob/b650083f/ql/src/test/results/clientpositive/merge_dynamic_partition5.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/merge_dynamic_partition5.q.out b/ql/src/test/results/clientpositive/merge_dynamic_partition5.q.out index db782cb..89265fd 100644 --- a/ql/src/test/results/clientpositive/merge_dynamic_partition5.q.out +++ b/ql/src/test/results/clientpositive/merge_dynamic_partition5.q.out @@ -116,13 +116,14 @@ POSTHOOK: Input: default@srcpart_merge_dp_rc@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart_merge_dp_rc@ds=2008-04-08/hr=12 STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 - Stage-4 - Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 - Stage-2 depends on stages: Stage-0 - Stage-3 + Stage-2 depends on stages: Stage-1 + Stage-8 depends on stages: Stage-2 , consists of Stage-5, Stage-4, Stage-6 Stage-5 - Stage-6 depends on stages: Stage-5 + Stage-0 depends on stages: Stage-5, Stage-4, Stage-7 + Stage-3 depends on stages: Stage-0 + Stage-4 + Stage-6 + Stage-7 depends on stages: Stage-6 STAGE PLANS: Stage: Stage-1 @@ -136,11 +137,56 @@ STAGE PLANS: expressions: key (type: string), value (type: string), if(((UDFToDouble(key) % 100.0D) = 0.0D), 'a1', 'b1') (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 618 Data size: 5934 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: string) - sort order: + - Map-reduce partition columns: _col2 (type: string) - value expressions: _col0 (type: string), _col1 (type: string) + Select Operator + expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), _col2 (type: string) + outputColumnNames: key, value, ds, hr + Statistics: Num rows: 618 Data size: 5934 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string), hr (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 618 Data size: 5934 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: 618 Data size: 5934 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + 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 + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 309 Data size: 2967 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 309 Data size: 2967 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 309 Data size: 2967 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-2 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + key expressions: _col2 (type: string) + sort order: + + Map-reduce partition columns: _col2 (type: string) + value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY._col2 (type: string) @@ -155,10 +201,10 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe name: default.merge_dynamic_part - Stage: Stage-7 + Stage: Stage-8 Conditional Operator - Stage: Stage-4 + Stage: Stage-5 Move Operator files: hdfs directory: true @@ -177,7 +223,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe name: default.merge_dynamic_part - Stage: Stage-2 + Stage: Stage-3 Stats Work Basic Stats Work: Column Stats Desc: @@ -185,21 +231,21 @@ STAGE PLANS: Column Types: string, string Table: default.merge_dynamic_part - Stage: Stage-3 + Stage: Stage-4 Merge File Operator Map Operator Tree: RCFile Merge Operator merge level: block input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat - Stage: Stage-5 + Stage: Stage-6 Merge File Operator Map Operator Tree: RCFile Merge Operator merge level: block input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat - Stage: Stage-6 + Stage: Stage-7 Move Operator files: hdfs directory: true http://git-wip-us.apache.org/repos/asf/hive/blob/b650083f/ql/src/test/results/clientpositive/orc_merge10.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/orc_merge10.q.out b/ql/src/test/results/clientpositive/orc_merge10.q.out index 0184fa9..3e0a3bd 100644 --- a/ql/src/test/results/clientpositive/orc_merge10.q.out +++ b/ql/src/test/results/clientpositive/orc_merge10.q.out @@ -55,8 +55,9 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - Stage-2 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-1 @@ -69,11 +70,56 @@ STAGE PLANS: expressions: UDFToInteger(key) (type: int), value (type: string), (hash(key) pmod 2) (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - value expressions: _col0 (type: int), _col1 (type: string) + Select Operator + expressions: _col0 (type: int), _col1 (type: string), '1' (type: string), CAST( _col2 AS STRING) (type: string) + outputColumnNames: key, value, ds, part + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string), part (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 500 Data size: 5312 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + 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 + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-2 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) + value expressions: _col0 (type: int), _col1 (type: string) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), KEY._col2 (type: int) @@ -101,7 +147,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.orcfile_merge1 - Stage: Stage-2 + Stage: Stage-3 Stats Work Basic Stats Work: Column Stats Desc: @@ -143,13 +189,14 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 - Stage-4 - Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 - Stage-2 depends on stages: Stage-0 - Stage-3 + Stage-2 depends on stages: Stage-1 + Stage-8 depends on stages: Stage-2 , consists of Stage-5, Stage-4, Stage-6 Stage-5 - Stage-6 depends on stages: Stage-5 + Stage-0 depends on stages: Stage-5, Stage-4, Stage-7 + Stage-3 depends on stages: Stage-0 + Stage-4 + Stage-6 + Stage-7 depends on stages: Stage-6 STAGE PLANS: Stage: Stage-1 @@ -162,11 +209,56 @@ STAGE PLANS: expressions: UDFToInteger(key) (type: int), value (type: string), (hash(key) pmod 2) (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - value expressions: _col0 (type: int), _col1 (type: string) + Select Operator + expressions: _col0 (type: int), _col1 (type: string), '1' (type: string), CAST( _col2 AS STRING) (type: string) + outputColumnNames: key, value, ds, part + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string), part (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 500 Data size: 5312 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + 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 + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-2 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) + value expressions: _col0 (type: int), _col1 (type: string) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), KEY._col2 (type: int) @@ -181,10 +273,10 @@ STAGE PLANS: serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.orcfile_merge1b - Stage: Stage-7 + Stage: Stage-8 Conditional Operator - Stage: Stage-4 + Stage: Stage-5 Move Operator files: hdfs directory: true @@ -203,7 +295,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.orcfile_merge1b - Stage: Stage-2 + Stage: Stage-3 Stats Work Basic Stats Work: Column Stats Desc: @@ -211,7 +303,7 @@ STAGE PLANS: Column Types: int, string Table: default.orcfile_merge1b - Stage: Stage-3 + Stage: Stage-4 Map Reduce Map Operator Tree: TableScan @@ -223,7 +315,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.orcfile_merge1b - Stage: Stage-5 + Stage: Stage-6 Map Reduce Map Operator Tree: TableScan @@ -235,7 +327,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.orcfile_merge1b - Stage: Stage-6 + Stage: Stage-7 Move Operator files: hdfs directory: true @@ -275,13 +367,14 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 - Stage-4 - Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 - Stage-2 depends on stages: Stage-0 - Stage-3 + Stage-2 depends on stages: Stage-1 + Stage-8 depends on stages: Stage-2 , consists of Stage-5, Stage-4, Stage-6 Stage-5 - Stage-6 depends on stages: Stage-5 + Stage-0 depends on stages: Stage-5, Stage-4, Stage-7 + Stage-3 depends on stages: Stage-0 + Stage-4 + Stage-6 + Stage-7 depends on stages: Stage-6 STAGE PLANS: Stage: Stage-1 @@ -294,11 +387,56 @@ STAGE PLANS: expressions: UDFToInteger(key) (type: int), value (type: string), (hash(key) pmod 2) (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - value expressions: _col0 (type: int), _col1 (type: string) + Select Operator + expressions: _col0 (type: int), _col1 (type: string), '1' (type: string), CAST( _col2 AS STRING) (type: string) + outputColumnNames: key, value, ds, part + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string), part (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 500 Data size: 5312 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + 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 + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-2 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) + value expressions: _col0 (type: int), _col1 (type: string) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), KEY._col2 (type: int) @@ -313,10 +451,10 @@ STAGE PLANS: serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.orcfile_merge1c - Stage: Stage-7 + Stage: Stage-8 Conditional Operator - Stage: Stage-4 + Stage: Stage-5 Move Operator files: hdfs directory: true @@ -335,7 +473,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.orcfile_merge1c - Stage: Stage-2 + Stage: Stage-3 Stats Work Basic Stats Work: Column Stats Desc: @@ -343,21 +481,21 @@ STAGE PLANS: Column Types: int, string Table: default.orcfile_merge1c - Stage: Stage-3 + Stage: Stage-4 Merge File Operator Map Operator Tree: ORC File Merge Operator merge level: stripe input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - Stage: Stage-5 + Stage: Stage-6 Merge File Operator Map Operator Tree: ORC File Merge Operator merge level: stripe input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - Stage: Stage-6 + Stage: Stage-7 Move Operator files: hdfs directory: true http://git-wip-us.apache.org/repos/asf/hive/blob/b650083f/ql/src/test/results/clientpositive/orc_merge2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/orc_merge2.q.out b/ql/src/test/results/clientpositive/orc_merge2.q.out index b91d981..7b58415 100644 --- a/ql/src/test/results/clientpositive/orc_merge2.q.out +++ b/ql/src/test/results/clientpositive/orc_merge2.q.out @@ -29,8 +29,9 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - Stage-2 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-1 @@ -43,11 +44,56 @@ STAGE PLANS: expressions: UDFToInteger(key) (type: int), value (type: string), (hash(key) pmod 10) (type: int), (hash(value) pmod 10) (type: int) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int), _col3 (type: int) - sort order: ++ - Map-reduce partition columns: _col2 (type: int), _col3 (type: int) - value expressions: _col0 (type: int), _col1 (type: string) + Select Operator + expressions: _col0 (type: int), _col1 (type: string), '1' (type: string), CAST( _col2 AS STRING) (type: string), CAST( _col3 AS STRING) (type: string) + outputColumnNames: key, value, one, two, three + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + keys: one (type: string), two (type: string), three (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + value expressions: _col3 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col4 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + 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 + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col3 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col4 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-2 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + key expressions: _col2 (type: int), _col3 (type: int) + sort order: ++ + Map-reduce partition columns: _col2 (type: int), _col3 (type: int) + value expressions: _col0 (type: int), _col1 (type: string) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), KEY._col2 (type: int), KEY._col3 (type: int) @@ -76,7 +122,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.orcfile_merge2a_n0 - Stage: Stage-2 + Stage: Stage-3 Stats Work Basic Stats Work: Column Stats Desc: http://git-wip-us.apache.org/repos/asf/hive/blob/b650083f/ql/src/test/results/clientpositive/orc_merge_diff_fs.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/orc_merge_diff_fs.q.out b/ql/src/test/results/clientpositive/orc_merge_diff_fs.q.out index d26cf05..561bec7 100644 --- a/ql/src/test/results/clientpositive/orc_merge_diff_fs.q.out +++ b/ql/src/test/results/clientpositive/orc_merge_diff_fs.q.out @@ -55,8 +55,9 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - Stage-2 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-1 @@ -69,11 +70,56 @@ STAGE PLANS: expressions: UDFToInteger(key) (type: int), value (type: string), (hash(key) pmod 2) (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - value expressions: _col0 (type: int), _col1 (type: string) + Select Operator + expressions: _col0 (type: int), _col1 (type: string), '1' (type: string), CAST( _col2 AS STRING) (type: string) + outputColumnNames: key, value, ds, part + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string), part (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 500 Data size: 5312 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + 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 + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-2 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) + value expressions: _col0 (type: int), _col1 (type: string) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), KEY._col2 (type: int) @@ -101,7 +147,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.orcfile_merge1_n0 - Stage: Stage-2 + Stage: Stage-3 Stats Work Basic Stats Work: Column Stats Desc: @@ -143,13 +189,14 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 - Stage-4 - Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 - Stage-2 depends on stages: Stage-0 - Stage-3 + Stage-2 depends on stages: Stage-1 + Stage-8 depends on stages: Stage-2 , consists of Stage-5, Stage-4, Stage-6 Stage-5 - Stage-6 depends on stages: Stage-5 + Stage-0 depends on stages: Stage-5, Stage-4, Stage-7 + Stage-3 depends on stages: Stage-0 + Stage-4 + Stage-6 + Stage-7 depends on stages: Stage-6 STAGE PLANS: Stage: Stage-1 @@ -162,11 +209,56 @@ STAGE PLANS: expressions: UDFToInteger(key) (type: int), value (type: string), (hash(key) pmod 2) (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - value expressions: _col0 (type: int), _col1 (type: string) + Select Operator + expressions: _col0 (type: int), _col1 (type: string), '1' (type: string), CAST( _col2 AS STRING) (type: string) + outputColumnNames: key, value, ds, part + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string), part (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 500 Data size: 5312 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + 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 + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-2 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) + value expressions: _col0 (type: int), _col1 (type: string) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), KEY._col2 (type: int) @@ -181,10 +273,10 @@ STAGE PLANS: serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.orcfile_merge1b_n0 - Stage: Stage-7 + Stage: Stage-8 Conditional Operator - Stage: Stage-4 + Stage: Stage-5 Move Operator files: hdfs directory: true @@ -203,7 +295,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.orcfile_merge1b_n0 - Stage: Stage-2 + Stage: Stage-3 Stats Work Basic Stats Work: Column Stats Desc: @@ -211,7 +303,7 @@ STAGE PLANS: Column Types: int, string Table: default.orcfile_merge1b_n0 - Stage: Stage-3 + Stage: Stage-4 Map Reduce Map Operator Tree: TableScan @@ -223,7 +315,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.orcfile_merge1b_n0 - Stage: Stage-5 + Stage: Stage-6 Map Reduce Map Operator Tree: TableScan @@ -235,7 +327,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.orcfile_merge1b_n0 - Stage: Stage-6 + Stage: Stage-7 Move Operator files: hdfs directory: true @@ -275,13 +367,14 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 - Stage-4 - Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 - Stage-2 depends on stages: Stage-0 - Stage-3 + Stage-2 depends on stages: Stage-1 + Stage-8 depends on stages: Stage-2 , consists of Stage-5, Stage-4, Stage-6 Stage-5 - Stage-6 depends on stages: Stage-5 + Stage-0 depends on stages: Stage-5, Stage-4, Stage-7 + Stage-3 depends on stages: Stage-0 + Stage-4 + Stage-6 + Stage-7 depends on stages: Stage-6 STAGE PLANS: Stage: Stage-1 @@ -294,11 +387,56 @@ STAGE PLANS: expressions: UDFToInteger(key) (type: int), value (type: string), (hash(key) pmod 2) (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - value expressions: _col0 (type: int), _col1 (type: string) + Select Operator + expressions: _col0 (type: int), _col1 (type: string), '1' (type: string), CAST( _col2 AS STRING) (type: string) + outputColumnNames: key, value, ds, part + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string), part (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 500 Data size: 5312 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + 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 + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-2 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) + value expressions: _col0 (type: int), _col1 (type: string) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), KEY._col2 (type: int) @@ -313,10 +451,10 @@ STAGE PLANS: serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.orcfile_merge1c_n0 - Stage: Stage-7 + Stage: Stage-8 Conditional Operator - Stage: Stage-4 + Stage: Stage-5 Move Operator files: hdfs directory: true @@ -335,7 +473,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.orcfile_merge1c_n0 - Stage: Stage-2 + Stage: Stage-3 Stats Work Basic Stats Work: Column Stats Desc: @@ -343,21 +481,21 @@ STAGE PLANS: Column Types: int, string Table: default.orcfile_merge1c_n0 - Stage: Stage-3 + Stage: Stage-4 Merge File Operator Map Operator Tree: ORC File Merge Operator merge level: stripe input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - Stage: Stage-5 + Stage: Stage-6 Merge File Operator Map Operator Tree: ORC File Merge Operator merge level: stripe input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - Stage: Stage-6 + Stage: Stage-7 Move Operator files: hdfs directory: true