http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/bucketsortoptimize_insert_8.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/bucketsortoptimize_insert_8.q.out b/ql/src/test/results/clientpositive/bucketsortoptimize_insert_8.q.out index 7f56cf3..dae491a 100644 --- a/ql/src/test/results/clientpositive/bucketsortoptimize_insert_8.q.out +++ b/ql/src/test/results/clientpositive/bucketsortoptimize_insert_8.q.out @@ -65,43 +65,13 @@ FROM test_table1 a JOIN test_table2 b ON a.key = b.key WHERE a.ds = '1' and b.ds = '1' POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-6 is a root stage , consists of Stage-7, Stage-8, Stage-1 - Stage-7 has a backup stage: Stage-1 - Stage-4 depends on stages: Stage-7 - Stage-0 depends on stages: Stage-1, Stage-4, Stage-5 - Stage-2 depends on stages: Stage-0 - Stage-8 has a backup stage: Stage-1 - Stage-5 depends on stages: Stage-8 - Stage-1 + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + Stage-2 depends on stages: Stage-0, Stage-3 + Stage-3 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-6 - Conditional Operator - - Stage: Stage-7 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_1:b - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_1:b - TableScan - alias: b - Statistics: Num rows: 84 Data size: 736 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 84 Data size: 736 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 84 Data size: 736 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - - Stage: Stage-4 + Stage: Stage-1 Map Reduce Map Operator Tree: TableScan @@ -114,7 +84,7 @@ STAGE PLANS: expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Map Join Operator + Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 keys: @@ -129,8 +99,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: int) value expressions: _col1 (type: int), _col2 (type: string) - Local Work: - Map Reduce Local Work Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: int), VALUE._col1 (type: string) @@ -142,6 +110,20 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.test_table3 + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), '1' (type: string) + outputColumnNames: key, key2, value, ds + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(key2, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + 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 Move Operator @@ -158,111 +140,35 @@ STAGE PLANS: Stage: Stage-2 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key, key2, value + Column Types: int, int, string + Table: default.test_table3 - Stage: Stage-8 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_0:a - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_0:a - TableScan - alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 84 Data size: 736 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 84 Data size: 736 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 84 Data size: 736 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col3, _col4 - Select Operator - expressions: _col0 (type: int), _col3 (type: int), concat(_col1, _col4) (type: string) - outputColumnNames: _col0, _col1, _col2 - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: int), _col2 (type: string) - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: int), VALUE._col1 (type: string) - outputColumnNames: _col0, _col1, _col2 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.test_table3 - - Stage: Stage-1 + Stage: Stage-3 Map Reduce Map Operator Tree: TableScan - alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Sorted Merge Bucket Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col3, _col4 - Select Operator - expressions: _col0 (type: int), _col3 (type: int), concat(_col1, _col4) (type: string) - outputColumnNames: _col0, _col1, _col2 - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: int), _col2 (type: string) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _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>) Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: int), VALUE._col1 (type: string) - outputColumnNames: _col0, _col1, _col2 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.test_table3 + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Select Operator + expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _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) + outputColumnNames: _col0, _col1, _col2, _col3 + 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.lazy.LazySimpleSerDe PREHOOK: query: INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') SELECT a.key, b.key, concat(a.value, b.value) @@ -274,9 +180,6 @@ PREHOOK: Input: default@test_table1@ds=1 PREHOOK: Input: default@test_table2 PREHOOK: Input: default@test_table2@ds=1 PREHOOK: Output: default@test_table3@ds=1 -Hive Runtime Error: Map local work failed -FAILED: Execution Error, return code 2 from org.apache.hadoop.hive.ql.exec.mr.MapredLocalTask -ATTEMPT: Execute BackupTask: org.apache.hadoop.hive.ql.exec.mr.MapRedTask POSTHOOK: query: INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') SELECT a.key, b.key, concat(a.value, b.value) FROM test_table1 a JOIN test_table2 b @@ -345,43 +248,13 @@ FROM test_table1 a JOIN test_table2 b ON a.key = b.key WHERE a.ds = '1' and b.ds = '1' POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-6 is a root stage , consists of Stage-7, Stage-8, Stage-1 - Stage-7 has a backup stage: Stage-1 - Stage-4 depends on stages: Stage-7 - Stage-0 depends on stages: Stage-1, Stage-4, Stage-5 - Stage-2 depends on stages: Stage-0 - Stage-8 has a backup stage: Stage-1 - Stage-5 depends on stages: Stage-8 - Stage-1 + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + Stage-2 depends on stages: Stage-0, Stage-3 + Stage-3 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-6 - Conditional Operator - - Stage: Stage-7 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_1:b - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_1:b - TableScan - alias: b - Statistics: Num rows: 84 Data size: 736 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 84 Data size: 736 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 84 Data size: 736 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - - Stage: Stage-4 + Stage: Stage-1 Map Reduce Map Operator Tree: TableScan @@ -394,7 +267,7 @@ STAGE PLANS: expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Map Join Operator + Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 keys: @@ -409,8 +282,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: int) value expressions: _col1 (type: int), _col2 (type: string) - Local Work: - Map Reduce Local Work Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: int), VALUE._col1 (type: string) @@ -422,6 +293,20 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.test_table3 + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), '1' (type: string) + outputColumnNames: key, key2, value, ds + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(key2, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + 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 Move Operator @@ -438,111 +323,35 @@ STAGE PLANS: Stage: Stage-2 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key, key2, value + Column Types: int, int, string + Table: default.test_table3 - Stage: Stage-8 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_0:a - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_0:a - TableScan - alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 84 Data size: 736 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 84 Data size: 736 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 84 Data size: 736 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col3, _col4 - Select Operator - expressions: _col3 (type: int), _col0 (type: int), concat(_col1, _col4) (type: string) - outputColumnNames: _col0, _col1, _col2 - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: int), _col2 (type: string) - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: int), VALUE._col1 (type: string) - outputColumnNames: _col0, _col1, _col2 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.test_table3 - - Stage: Stage-1 + Stage: Stage-3 Map Reduce Map Operator Tree: TableScan - alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Sorted Merge Bucket Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col3, _col4 - Select Operator - expressions: _col3 (type: int), _col0 (type: int), concat(_col1, _col4) (type: string) - outputColumnNames: _col0, _col1, _col2 - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: int), _col2 (type: string) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _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>) Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: int), VALUE._col1 (type: string) - outputColumnNames: _col0, _col1, _col2 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.test_table3 + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Select Operator + expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _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) + outputColumnNames: _col0, _col1, _col2, _col3 + 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.lazy.LazySimpleSerDe PREHOOK: query: INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') SELECT b.key, a.key, concat(a.value, b.value) @@ -554,9 +363,6 @@ PREHOOK: Input: default@test_table1@ds=1 PREHOOK: Input: default@test_table2 PREHOOK: Input: default@test_table2@ds=1 PREHOOK: Output: default@test_table3@ds=1 -Hive Runtime Error: Map local work failed -FAILED: Execution Error, return code 2 from org.apache.hadoop.hive.ql.exec.mr.MapredLocalTask -ATTEMPT: Execute BackupTask: org.apache.hadoop.hive.ql.exec.mr.MapRedTask POSTHOOK: query: INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') SELECT b.key, a.key, concat(a.value, b.value) FROM test_table1 a JOIN test_table2 b
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/case_sensitivity.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/case_sensitivity.q.out b/ql/src/test/results/clientpositive/case_sensitivity.q.out index c2f2f8b..c77994d 100644 --- a/ql/src/test/results/clientpositive/case_sensitivity.q.out +++ b/ql/src/test/results/clientpositive/case_sensitivity.q.out @@ -46,6 +46,32 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest1 + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 3 Data size: 837 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 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-7 Conditional Operator @@ -69,6 +95,10 @@ STAGE PLANS: Stage: Stage-2 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: int, string + Table: default.dest1 Stage: Stage-3 Map Reduce http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/cast1.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/cast1.q.out b/ql/src/test/results/clientpositive/cast1.q.out index a0cd142..9c23a76 100644 --- a/ql/src/test/results/clientpositive/cast1.q.out +++ b/ql/src/test/results/clientpositive/cast1.q.out @@ -44,6 +44,32 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest1 + Select Operator + expressions: _col0 (type: int), _col1 (type: double), _col2 (type: double), _col3 (type: double), _col4 (type: int), _col5 (type: string), _col6 (type: int) + outputColumnNames: c1, c2, c3, c4, c5, c6, c7 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll'), compute_stats(c4, 'hll'), compute_stats(c5, 'hll'), compute_stats(c6, 'hll'), compute_stats(c7, 'hll') + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 1 Data size: 2984 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 2984 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:binary>), _col4 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col5 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col6 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>) + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4), compute_stats(VALUE._col5), compute_stats(VALUE._col6) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 1 Data size: 3080 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 3080 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-7 Conditional Operator @@ -67,6 +93,10 @@ STAGE PLANS: Stage: Stage-2 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: c1, c2, c3, c4, c5, c6, c7 + Column Types: int, double, double, double, int, string, int + Table: default.dest1 Stage: Stage-3 Map Reduce http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/cbo_rp_annotate_stats_groupby.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/cbo_rp_annotate_stats_groupby.q.out b/ql/src/test/results/clientpositive/cbo_rp_annotate_stats_groupby.q.out index eac491e..3d92a0d 100644 --- a/ql/src/test/results/clientpositive/cbo_rp_annotate_stats_groupby.q.out +++ b/ql/src/test/results/clientpositive/cbo_rp_annotate_stats_groupby.q.out @@ -66,11 +66,11 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc - Statistics: Num rows: 8 Data size: 1600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) outputColumnNames: state, locid, zip, year - Statistics: Num rows: 8 Data size: 1600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: analyze table loc_orc compute statistics for columns state @@ -108,22 +108,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: sq1:loc_orc - Statistics: Num rows: 8 Data size: 720 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 720 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int) outputColumnNames: state, locid - Statistics: Num rows: 8 Data size: 720 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 720 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: state (type: string), locid (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 8 Data size: 784 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 784 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: int) - Statistics: Num rows: 8 Data size: 784 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 784 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Reduce Operator Tree: Group By Operator @@ -131,13 +131,13 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: int) mode: mergepartial outputColumnNames: state, locid, $f2 - Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 784 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: min(locid) keys: state (type: string), $f2 (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 784 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -153,7 +153,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: bigint) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint) - Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 784 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: int) Reduce Operator Tree: Group By Operator @@ -161,10 +161,10 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: bigint) mode: mergepartial outputColumnNames: state, $f2, $f2_0 - Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 784 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 784 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -739,30 +739,30 @@ STAGE PLANS: Map Operator Tree: TableScan alias: loc_orc - Statistics: Num rows: 8 Data size: 752 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 752 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), zip (type: bigint) outputColumnNames: state, zip - Statistics: Num rows: 8 Data size: 752 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 752 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: state (type: string), zip (type: bigint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 376 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 4 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: bigint) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint) - Statistics: Num rows: 4 Data size: 376 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 4 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: bigint) mode: mergepartial outputColumnNames: state, zip - Statistics: Num rows: 4 Data size: 376 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 4 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 376 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 4 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/cbo_rp_auto_join17.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/cbo_rp_auto_join17.q.out b/ql/src/test/results/clientpositive/cbo_rp_auto_join17.q.out index d3747af..5fbc878 100644 --- a/ql/src/test/results/clientpositive/cbo_rp_auto_join17.q.out +++ b/ql/src/test/results/clientpositive/cbo_rp_auto_join17.q.out @@ -15,13 +15,14 @@ FROM src src1 JOIN src src2 ON (src1.key = src2.key) INSERT OVERWRITE TABLE dest1 SELECT src1.*, src2.* POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-5 is a root stage - Stage-4 depends on stages: Stage-5 - Stage-0 depends on stages: Stage-4 - Stage-2 depends on stages: Stage-0 + Stage-6 is a root stage + Stage-5 depends on stages: Stage-6 + Stage-0 depends on stages: Stage-5 + Stage-2 depends on stages: Stage-0, Stage-3 + Stage-3 depends on stages: Stage-5 STAGE PLANS: - Stage: Stage-5 + Stage: Stage-6 Map Reduce Local Work Alias -> Map Local Tables: src1 @@ -44,7 +45,7 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) - Stage: Stage-4 + Stage: Stage-5 Map Reduce Map Operator Tree: TableScan @@ -77,6 +78,21 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest1 + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string) + outputColumnNames: key1, value1, key2, value2 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(key1, 'hll'), compute_stats(value1, 'hll'), compute_stats(key2, 'hll'), compute_stats(value2, 'hll') + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -93,6 +109,36 @@ STAGE PLANS: Stage: Stage-2 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key1, value1, key2, value2 + Column Types: int, string, int, string + Table: default.dest1 + + Stage: Stage-3 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _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>) + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _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>) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1760 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 PREHOOK: query: FROM src src1 JOIN src src2 ON (src1.key = src2.key) INSERT OVERWRITE TABLE dest1 SELECT src1.*, src2.* http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/cbo_rp_gby2_map_multi_distinct.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/cbo_rp_gby2_map_multi_distinct.q.out b/ql/src/test/results/clientpositive/cbo_rp_gby2_map_multi_distinct.q.out index e5d4421..68628fe 100644 --- a/ql/src/test/results/clientpositive/cbo_rp_gby2_map_multi_distinct.q.out +++ b/ql/src/test/results/clientpositive/cbo_rp_gby2_map_multi_distinct.q.out @@ -21,7 +21,8 @@ POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 - Stage-2 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-0, Stage-3 + Stage-3 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-1 @@ -65,6 +66,21 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest1 + Select Operator + expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int) + outputColumnNames: key, c1, c2, c3, c4 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll'), compute_stats(c4, 'hll') + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1 Data size: 2192 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 Move Operator @@ -79,6 +95,36 @@ STAGE PLANS: Stage: Stage-2 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key, c1, c2, c3, c4 + Column Types: string, int, string, int, int + Table: default.dest1 + + Stage: Stage-3 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 2192 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col4 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>) + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1 Data size: 2240 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col4 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1 Data size: 2240 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 2240 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 PREHOOK: query: FROM src INSERT OVERWRITE TABLE dest1 @@ -132,7 +178,8 @@ POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 - Stage-2 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-0, Stage-3 + Stage-3 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-1 @@ -176,6 +223,21 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest1 + Select Operator + expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int) + outputColumnNames: key, c1, c2, c3, c4 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll'), compute_stats(c4, 'hll') + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1 Data size: 2192 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 Move Operator @@ -190,6 +252,36 @@ STAGE PLANS: Stage: Stage-2 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key, c1, c2, c3, c4 + Column Types: string, int, string, int, int + Table: default.dest1 + + Stage: Stage-3 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 2192 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col4 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>) + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1 Data size: 2240 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col4 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1 Data size: 2240 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 2240 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 PREHOOK: query: FROM src INSERT OVERWRITE TABLE dest1 http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/cbo_rp_groupby3_noskew_multi_distinct.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/cbo_rp_groupby3_noskew_multi_distinct.q.out b/ql/src/test/results/clientpositive/cbo_rp_groupby3_noskew_multi_distinct.q.out index 177eefd..bece89f 100644 --- a/ql/src/test/results/clientpositive/cbo_rp_groupby3_noskew_multi_distinct.q.out +++ b/ql/src/test/results/clientpositive/cbo_rp_groupby3_noskew_multi_distinct.q.out @@ -74,6 +74,26 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest1 + Select Operator + expressions: _col0 (type: double), _col1 (type: double), _col2 (type: double), _col3 (type: double), _col4 (type: double), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: double), _col10 (type: double) + outputColumnNames: c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11 + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll'), compute_stats(c4, 'hll'), compute_stats(c5, 'hll'), compute_stats(c6, 'hll'), compute_stats(c7, 'hll'), compute_stats(c8, 'hll'), compute_stats(c9, 'hll'), compute_stats(c10, 'hll'), compute_stats(c11, 'hll') + mode: complete + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 + Statistics: Num rows: 1 Data size: 5280 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col1 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col4 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col5 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col6 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col7 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,numdis tinctvalues:bigint,ndvbitvector:binary>), _col8 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col9 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col10 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 + Statistics: Num rows: 1 Data size: 5280 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 5280 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-0 Move Operator @@ -88,6 +108,10 @@ STAGE PLANS: Stage: Stage-2 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11 + Column Types: double, double, double, double, double, double, double, double, double, double, double + Table: default.dest1 PREHOOK: query: FROM src INSERT OVERWRITE TABLE dest1 SELECT http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/constprog_dp.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/constprog_dp.q.out b/ql/src/test/results/clientpositive/constprog_dp.q.out index 86b6c32..4ed3ebf 100644 --- a/ql/src/test/results/clientpositive/constprog_dp.q.out +++ b/ql/src/test/results/clientpositive/constprog_dp.q.out @@ -43,6 +43,40 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + outputColumnNames: key, value, ds + 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) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1000 Data size: 10624 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: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string) + outputColumnNames: _col0, _col1, _col2 + 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-7 Conditional Operator @@ -68,6 +102,10 @@ STAGE PLANS: Stage: Stage-2 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.dest Stage: Stage-3 Map Reduce http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/cp_sel.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/cp_sel.q.out b/ql/src/test/results/clientpositive/cp_sel.q.out index 9100037..d467b18 100644 --- a/ql/src/test/results/clientpositive/cp_sel.q.out +++ b/ql/src/test/results/clientpositive/cp_sel.q.out @@ -81,7 +81,8 @@ POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 - Stage-2 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-0, Stage-3 + Stage-3 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-1 @@ -113,6 +114,22 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.testpartbucket + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (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 + 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 Move Operator @@ -130,6 +147,39 @@ STAGE PLANS: Stage: Stage-2 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.testpartbucket + + Stage: Stage-3 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 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>) + 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 PREHOOK: query: insert overwrite table testpartbucket partition(ds,hr) select key,value,'hello' as ds, 'world' as hr from srcpart where hr=11 PREHOOK: type: QUERY http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/deleteAnalyze.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/deleteAnalyze.q.out b/ql/src/test/results/clientpositive/deleteAnalyze.q.out index 1d051fd..783039b 100644 --- a/ql/src/test/results/clientpositive/deleteAnalyze.q.out +++ b/ql/src/test/results/clientpositive/deleteAnalyze.q.out @@ -47,7 +47,7 @@ Retention: 0 #### A masked pattern was here #### Table Type: MANAGED_TABLE Table Parameters: - COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"amount\":\"true\",\"id\":\"true\",\"item\":\"true\",\"sales_tax\":\"true\"}} numFiles 1 numRows 2 rawDataSize 634 @@ -73,17 +73,17 @@ POSTHOOK: type: DESCTABLE POSTHOOK: Input: default@testdeci2 col_name amount data_type decimal(10,3) -min -max -num_nulls -distinct_count +min 12.123 +max 123.123 +num_nulls 0 +distinct_count 2 avg_col_len max_col_len num_trues num_falses -bitVector +bitVector HL comment from deserializer -COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} +COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"amount\":\"true\",\"id\":\"true\",\"item\":\"true\",\"sales_tax\":\"true\"}} PREHOOK: query: analyze table testdeci2 compute statistics for columns PREHOOK: type: QUERY PREHOOK: Input: default@testdeci2 http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/dynamic_partition_skip_default.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/dynamic_partition_skip_default.q.out b/ql/src/test/results/clientpositive/dynamic_partition_skip_default.q.out index d199574..b4efaf4 100644 --- a/ql/src/test/results/clientpositive/dynamic_partition_skip_default.q.out +++ b/ql/src/test/results/clientpositive/dynamic_partition_skip_default.q.out @@ -61,7 +61,7 @@ STAGE PLANS: partcol1 1 partcol2 1 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"intcol":"true"}} bucket_count -1 column.name.delimiter , columns intcol @@ -130,7 +130,7 @@ STAGE PLANS: partcol1 1 partcol2 1 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"intcol":"true"}} bucket_count -1 column.name.delimiter , columns intcol @@ -199,7 +199,7 @@ STAGE PLANS: partcol1 1 partcol2 1 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"intcol":"true"}} bucket_count -1 column.name.delimiter , columns intcol @@ -245,7 +245,7 @@ STAGE PLANS: partcol1 1 partcol2 __HIVE_DEFAULT_PARTITION__ properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"intcol":"true"}} bucket_count -1 column.name.delimiter , columns intcol http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/dynpart_sort_optimization_acid2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/dynpart_sort_optimization_acid2.q.out b/ql/src/test/results/clientpositive/dynpart_sort_optimization_acid2.q.out index 8199235..884e63c 100644 --- a/ql/src/test/results/clientpositive/dynpart_sort_optimization_acid2.q.out +++ b/ql/src/test/results/clientpositive/dynpart_sort_optimization_acid2.q.out @@ -71,4 +71,8 @@ STAGE PLANS: Stage: Stage-2 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.non_acid http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/encrypted/encryption_join_unencrypted_tbl.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/encrypted/encryption_join_unencrypted_tbl.q.out b/ql/src/test/results/clientpositive/encrypted/encryption_join_unencrypted_tbl.q.out index f1654d4..20e753e 100644 --- a/ql/src/test/results/clientpositive/encrypted/encryption_join_unencrypted_tbl.q.out +++ b/ql/src/test/results/clientpositive/encrypted/encryption_join_unencrypted_tbl.q.out @@ -595,7 +595,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} bucket_count -1 column.name.delimiter , columns key,value @@ -616,7 +616,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} bucket_count -1 column.name.delimiter , columns key,value http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/explain_ddl.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/explain_ddl.q.out b/ql/src/test/results/clientpositive/explain_ddl.q.out index 8a17a66..6506e89 100644 --- a/ql/src/test/results/clientpositive/explain_ddl.q.out +++ b/ql/src/test/results/clientpositive/explain_ddl.q.out @@ -521,6 +521,32 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.m1 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + 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') + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 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-7 Conditional Operator @@ -544,6 +570,10 @@ STAGE PLANS: Stage: Stage-2 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.m1 Stage: Stage-3 Map Reduce http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/extrapolate_part_stats_full.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/extrapolate_part_stats_full.q.out b/ql/src/test/results/clientpositive/extrapolate_part_stats_full.q.out index 25f5372..deda5a0 100644 --- a/ql/src/test/results/clientpositive/extrapolate_part_stats_full.q.out +++ b/ql/src/test/results/clientpositive/extrapolate_part_stats_full.q.out @@ -119,7 +119,7 @@ STAGE PLANS: partition values: year 2000 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true"}} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true","zip":"true"}} bucket_count -1 column.name.delimiter , columns state,locid,zip @@ -164,7 +164,7 @@ STAGE PLANS: partition values: year 2001 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true"}} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true","zip":"true"}} bucket_count -1 column.name.delimiter , columns state,locid,zip @@ -232,7 +232,7 @@ STAGE PLANS: partition values: year 2000 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true"}} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true","zip":"true"}} bucket_count -1 column.name.delimiter , columns state,locid,zip @@ -277,7 +277,7 @@ STAGE PLANS: partition values: year 2001 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true"}} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true","zip":"true"}} bucket_count -1 column.name.delimiter , columns state,locid,zip