You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by kg...@apache.org on 2019/01/23 16:38:52 UTC
[20/51] [partial] hive git commit: HIVE-17084: Turn on
hive.stats.fetch.column.stats configuration flag (Zoltan Haindrich reviewed
by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/268a6e5a/ql/src/test/results/clientpositive/groupby2_map.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby2_map.q.out b/ql/src/test/results/clientpositive/groupby2_map.q.out
index 786c30e..d3c4870 100644
--- a/ql/src/test/results/clientpositive/groupby2_map.q.out
+++ b/ql/src/test/results/clientpositive/groupby2_map.q.out
@@ -30,22 +30,22 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: substr(key, 1, 1) (type: string), substr(value, 5) (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(DISTINCT _col1), sum(_col1)
keys: _col0 (type: string), _col1 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 96000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 96000 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: double)
Reduce Operator Tree:
Group By Operator
@@ -53,14 +53,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 50000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -69,12 +69,12 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string)
outputColumnNames: key, c1, c2
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: compute_stats(key, 'hll'), compute_stats(c1, 'hll'), compute_stats(c2, 'hll')
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 1312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -106,7 +106,7 @@ STAGE PLANS:
TableScan
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 1312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE
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>)
Execution mode: vectorized
Reduce Operator Tree:
@@ -114,10 +114,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1320 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/268a6e5a/ql/src/test/results/clientpositive/groupby2_map_multi_distinct.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby2_map_multi_distinct.q.out b/ql/src/test/results/clientpositive/groupby2_map_multi_distinct.q.out
index 3764b53..d9b0d05 100644
--- a/ql/src/test/results/clientpositive/groupby2_map_multi_distinct.q.out
+++ b/ql/src/test/results/clientpositive/groupby2_map_multi_distinct.q.out
@@ -30,22 +30,22 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: substr(key, 1, 1) (type: string), substr(value, 5) (type: string), value (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(DISTINCT _col1), sum(_col1), sum(DISTINCT _col1), count(_col2)
keys: _col0 (type: string), _col1 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 100000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 100000 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: double), _col5 (type: bigint)
Reduce Operator Tree:
Group By Operator
@@ -53,14 +53,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 54000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string), UDFToInteger(_col3) (type: int), UDFToInteger(_col4) (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -69,12 +69,12 @@ STAGE PLANS:
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
+ Statistics: Num rows: 250 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE
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: 2160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 2152 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -106,7 +106,7 @@ STAGE PLANS:
TableScan
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 2160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 2152 Basic stats: COMPLETE Column stats: COMPLETE
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>)
Execution mode: vectorized
Reduce Operator Tree:
@@ -114,10 +114,10 @@ STAGE PLANS:
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: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -180,22 +180,22 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: substr(key, 1, 1) (type: string), substr(value, 5) (type: string), value (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(DISTINCT _col0), sum(_col1), sum(DISTINCT _col1), count(_col2)
keys: _col0 (type: string), _col1 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 100000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 100000 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: double), _col5 (type: bigint)
Reduce Operator Tree:
Group By Operator
@@ -203,14 +203,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 54000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string), UDFToInteger(_col3) (type: int), UDFToInteger(_col4) (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -219,12 +219,12 @@ STAGE PLANS:
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
+ Statistics: Num rows: 250 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE
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: 2160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 2152 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -256,7 +256,7 @@ STAGE PLANS:
TableScan
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 2160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 2152 Basic stats: COMPLETE Column stats: COMPLETE
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>)
Execution mode: vectorized
Reduce Operator Tree:
@@ -264,10 +264,10 @@ STAGE PLANS:
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: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 2200 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/268a6e5a/ql/src/test/results/clientpositive/groupby2_map_skew.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby2_map_skew.q.out b/ql/src/test/results/clientpositive/groupby2_map_skew.q.out
index 2f3b1df..5b6c053 100644
--- a/ql/src/test/results/clientpositive/groupby2_map_skew.q.out
+++ b/ql/src/test/results/clientpositive/groupby2_map_skew.q.out
@@ -31,22 +31,22 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: substr(key, 1, 1) (type: string), substr(value, 5) (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(DISTINCT _col1), sum(_col1)
keys: _col0 (type: string), _col1 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 96000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 96000 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: double)
Reduce Operator Tree:
Group By Operator
@@ -54,7 +54,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: partials
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 50000 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -70,7 +70,7 @@ STAGE PLANS:
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 50000 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint), _col2 (type: double)
Execution mode: vectorized
Reduce Operator Tree:
@@ -79,14 +79,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: final
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 50000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -95,12 +95,12 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string)
outputColumnNames: key, c1, c2
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: compute_stats(key, 'hll'), compute_stats(c1, 'hll'), compute_stats(c2, 'hll')
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 1312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -132,7 +132,7 @@ STAGE PLANS:
TableScan
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 1312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE
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>)
Execution mode: vectorized
Reduce Operator Tree:
@@ -140,10 +140,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
mode: final
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1320 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/268a6e5a/ql/src/test/results/clientpositive/groupby2_noskew.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby2_noskew.q.out b/ql/src/test/results/clientpositive/groupby2_noskew.q.out
index 34e9e68..9fcf966 100644
--- a/ql/src/test/results/clientpositive/groupby2_noskew.q.out
+++ b/ql/src/test/results/clientpositive/groupby2_noskew.q.out
@@ -30,16 +30,16 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: substr(key, 1, 1) (type: string), substr(value, 5) (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
@@ -47,14 +47,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: complete
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 63200 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 117552 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 117552 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -63,7 +63,7 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string)
outputColumnNames: key, c1, c2
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 117552 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -95,7 +95,7 @@ STAGE PLANS:
TableScan
Reduce Output Operator
sort order:
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 117552 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: key (type: string), c1 (type: int), c2 (type: string)
Execution mode: vectorized
Reduce Operator Tree:
@@ -103,10 +103,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll'), compute_stats(VALUE._col3, 'hll')
mode: complete
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1320 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/268a6e5a/ql/src/test/results/clientpositive/groupby2_noskew_multi_distinct.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby2_noskew_multi_distinct.q.out b/ql/src/test/results/clientpositive/groupby2_noskew_multi_distinct.q.out
index 445aee6..cb4bf90 100644
--- a/ql/src/test/results/clientpositive/groupby2_noskew_multi_distinct.q.out
+++ b/ql/src/test/results/clientpositive/groupby2_noskew_multi_distinct.q.out
@@ -30,16 +30,16 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: substr(key, 1, 1) (type: string), substr(value, 5) (type: string), value (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: string)
Execution mode: vectorized
Reduce Operator Tree:
@@ -48,14 +48,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: complete
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 68256 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string), UDFToInteger(_col3) (type: int), UDFToInteger(_col4) (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 120080 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 120080 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -64,7 +64,7 @@ STAGE PLANS:
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
+ Statistics: Num rows: 316 Data size: 120080 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -96,7 +96,7 @@ STAGE PLANS:
TableScan
Reduce Output Operator
sort order:
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 120080 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: key (type: string), c1 (type: int), c2 (type: string), c3 (type: int), c4 (type: int)
Execution mode: vectorized
Reduce Operator Tree:
@@ -104,10 +104,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll'), compute_stats(VALUE._col3, 'hll'), compute_stats(VALUE._col4, 'hll'), compute_stats(VALUE._col5, 'hll')
mode: complete
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 2200 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/268a6e5a/ql/src/test/results/clientpositive/groupby3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby3.q.out b/ql/src/test/results/clientpositive/groupby3.q.out
index 30f81df..22ad867 100644
--- a/ql/src/test/results/clientpositive/groupby3.q.out
+++ b/ql/src/test/results/clientpositive/groupby3.q.out
@@ -49,23 +49,23 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: value (type: string)
outputColumnNames: value
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: substr(value, 5) (type: string)
sort order: +
Map-reduce partition columns: substr(value, 5) (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
aggregations: sum(KEY._col0:0._col0), avg(KEY._col0:0._col0), avg(DISTINCT KEY._col0:0._col0), max(KEY._col0:0._col0), min(KEY._col0:0._col0), std(KEY._col0:0._col0), stddev_samp(KEY._col0:0._col0), variance(KEY._col0:0._col0), var_samp(KEY._col0:0._col0)
mode: partial1
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 1 Data size: 1208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1208 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -80,7 +80,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Map-reduce partition columns: rand() (type: double)
- Statistics: Num rows: 1 Data size: 1208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1208 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: double), _col1 (type: struct<count:bigint,sum:double,input:string>), _col2 (type: struct<count:bigint,sum:double,input:string>), _col3 (type: string), _col4 (type: string), _col5 (type: struct<count:bigint,sum:double,variance:double>), _col6 (type: struct<count:bigint,sum:double,variance:double>), _col7 (type: struct<count:bigint,sum:double,variance:double>), _col8 (type: struct<count:bigint,sum:double,variance:double>)
Execution mode: vectorized
Reduce Operator Tree:
@@ -88,14 +88,14 @@ STAGE PLANS:
aggregations: sum(VALUE._col0), avg(VALUE._col1), avg(VALUE._col2), max(VALUE._col3), min(VALUE._col4), std(VALUE._col5), stddev_samp(VALUE._col6), variance(VALUE._col7), var_samp(VALUE._col8)
mode: final
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 1 Data size: 1208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: double), _col1 (type: double), _col2 (type: double), UDFToDouble(_col3) (type: double), UDFToDouble(_col4) (type: double), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 1 Data size: 1208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 1208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -104,12 +104,12 @@ STAGE PLANS:
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)
outputColumnNames: c1, c2, c3, c4, c5, c6, c7, c8, c9
- Statistics: Num rows: 1 Data size: 1208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
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')
mode: complete
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 1 Data size: 3984 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 3816 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -141,7 +141,7 @@ STAGE PLANS:
TableScan
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 3984 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 3816 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: struct<columntype:string,min:double,max:double,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:double,max:double,countnulls:bigint,bitvector:binary>), _col5 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:binary>), _col6 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:binary>), _col7 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:binary>), _col8 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:binary>)
Execution mode: vectorized
Reduce Operator Tree:
@@ -149,10 +149,10 @@ STAGE PLANS:
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), compute_stats(VALUE._col7), compute_stats(VALUE._col8)
mode: final
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 1 Data size: 4128 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 3960 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 4128 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 3960 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/268a6e5a/ql/src/test/results/clientpositive/groupby3_map.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby3_map.q.out b/ql/src/test/results/clientpositive/groupby3_map.q.out
index 328711a..5b66bb2 100644
--- a/ql/src/test/results/clientpositive/groupby3_map.q.out
+++ b/ql/src/test/results/clientpositive/groupby3_map.q.out
@@ -47,35 +47,35 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: substr(value, 5) (type: string), UDFToDouble(substr(value, 5)) (type: double), (UDFToDouble(substr(value, 5)) * UDFToDouble(substr(value, 5))) (type: double)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(_col0), count(_col0), sum(DISTINCT _col0), count(DISTINCT _col0), max(_col0), min(_col0), sum(_col2), sum(_col1)
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 150000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 150000 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: double), _col2 (type: bigint), _col5 (type: string), _col6 (type: string), _col7 (type: double), _col8 (type: double)
Reduce Operator Tree:
Group By Operator
aggregations: sum(VALUE._col0), count(VALUE._col1), sum(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), max(VALUE._col4), min(VALUE._col5), sum(VALUE._col6), sum(VALUE._col7)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
- Statistics: Num rows: 1 Data size: 516 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 416 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: double), (_col0 / _col1) (type: double), (_col2 / _col3) (type: double), UDFToDouble(_col4) (type: double), UDFToDouble(_col5) (type: double), power(((_col6 - ((_col7 * _col7) / _col1)) / _col1), 0.5) (type: double), power(((_col6 - ((_col7 * _col7) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END), 0.5) (type: double), ((_col6 - ((_col7 * _col7) / _col1)) / _col1) (type: double), ((_col6 - ((_col7 * _col7) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 1 Data size: 516 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 516 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -84,19 +84,19 @@ STAGE PLANS:
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)
outputColumnNames: c1, c2, c3, c4, c5, c6, c7, c8, c9
- Statistics: Num rows: 1 Data size: 516 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
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')
mode: complete
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 1 Data size: 3984 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 3816 Basic stats: COMPLETE Column stats: COMPLETE
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>)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 1 Data size: 3984 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 3816 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 3984 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 3816 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/268a6e5a/ql/src/test/results/clientpositive/groupby3_map_multi_distinct.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby3_map_multi_distinct.q.out b/ql/src/test/results/clientpositive/groupby3_map_multi_distinct.q.out
index 2bba736..39059da 100644
--- a/ql/src/test/results/clientpositive/groupby3_map_multi_distinct.q.out
+++ b/ql/src/test/results/clientpositive/groupby3_map_multi_distinct.q.out
@@ -51,35 +51,35 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: substr(value, 5) (type: string), UDFToDouble(substr(value, 5)) (type: double), (UDFToDouble(substr(value, 5)) * UDFToDouble(substr(value, 5))) (type: double)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(_col0), count(_col0), sum(DISTINCT _col0), count(DISTINCT _col0), max(_col0), min(_col0), sum(_col2), sum(_col1)
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 150000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 150000 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: double), _col2 (type: bigint), _col5 (type: string), _col6 (type: string), _col7 (type: double), _col8 (type: double)
Reduce Operator Tree:
Group By Operator
aggregations: sum(VALUE._col0), count(VALUE._col1), sum(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), max(VALUE._col4), min(VALUE._col5), sum(VALUE._col6), sum(VALUE._col7)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
- Statistics: Num rows: 1 Data size: 516 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 416 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: double), (_col0 / _col1) (type: double), (_col2 / _col3) (type: double), UDFToDouble(_col4) (type: double), UDFToDouble(_col5) (type: double), power(((_col6 - ((_col7 * _col7) / _col1)) / _col1), 0.5) (type: double), power(((_col6 - ((_col7 * _col7) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END), 0.5) (type: double), ((_col6 - ((_col7 * _col7) / _col1)) / _col1) (type: double), ((_col6 - ((_col7 * _col7) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END) (type: double), _col2 (type: double), UDFToDouble(_col3) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
- Statistics: Num rows: 1 Data size: 516 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 516 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -88,19 +88,19 @@ STAGE PLANS:
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: 516 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
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: 4832 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 4664 Basic stats: COMPLETE Column stats: COMPLETE
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: 4832 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 4664 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 4832 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 4664 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/268a6e5a/ql/src/test/results/clientpositive/groupby3_map_skew.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby3_map_skew.q.out b/ql/src/test/results/clientpositive/groupby3_map_skew.q.out
index a699c58..7203248 100644
--- a/ql/src/test/results/clientpositive/groupby3_map_skew.q.out
+++ b/ql/src/test/results/clientpositive/groupby3_map_skew.q.out
@@ -48,29 +48,29 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: value (type: string)
outputColumnNames: value
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(substr(value, 5)), avg(substr(value, 5)), avg(DISTINCT substr(value, 5)), max(substr(value, 5)), min(substr(value, 5)), std(substr(value, 5)), stddev_samp(substr(value, 5)), variance(substr(value, 5)), var_samp(substr(value, 5))
keys: substr(value, 5) (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 348000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 348000 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: double), _col2 (type: struct<count:bigint,sum:double,input:string>), _col4 (type: string), _col5 (type: string), _col6 (type: struct<count:bigint,sum:double,variance:double>), _col7 (type: struct<count:bigint,sum:double,variance:double>), _col8 (type: struct<count:bigint,sum:double,variance:double>), _col9 (type: struct<count:bigint,sum:double,variance:double>)
Reduce Operator Tree:
Group By Operator
aggregations: sum(VALUE._col0), avg(VALUE._col1), avg(DISTINCT KEY._col0:0._col0), max(VALUE._col3), min(VALUE._col4), std(VALUE._col5), stddev_samp(VALUE._col6), variance(VALUE._col7), var_samp(VALUE._col8)
mode: partials
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 1 Data size: 1464 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1208 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -84,7 +84,7 @@ STAGE PLANS:
TableScan
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 1464 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1208 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: double), _col1 (type: struct<count:bigint,sum:double,input:string>), _col2 (type: struct<count:bigint,sum:double,input:string>), _col3 (type: string), _col4 (type: string), _col5 (type: struct<count:bigint,sum:double,variance:double>), _col6 (type: struct<count:bigint,sum:double,variance:double>), _col7 (type: struct<count:bigint,sum:double,variance:double>), _col8 (type: struct<count:bigint,sum:double,variance:double>)
Execution mode: vectorized
Reduce Operator Tree:
@@ -92,14 +92,14 @@ STAGE PLANS:
aggregations: sum(VALUE._col0), avg(VALUE._col1), avg(VALUE._col2), max(VALUE._col3), min(VALUE._col4), std(VALUE._col5), stddev_samp(VALUE._col6), variance(VALUE._col7), var_samp(VALUE._col8)
mode: final
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 1 Data size: 1464 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: double), _col1 (type: double), _col2 (type: double), UDFToDouble(_col3) (type: double), UDFToDouble(_col4) (type: double), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 1 Data size: 1464 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 1464 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -108,19 +108,19 @@ STAGE PLANS:
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)
outputColumnNames: c1, c2, c3, c4, c5, c6, c7, c8, c9
- Statistics: Num rows: 1 Data size: 1464 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
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')
mode: complete
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 1 Data size: 4064 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 3816 Basic stats: COMPLETE Column stats: COMPLETE
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>)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 1 Data size: 4064 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 3816 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 4064 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 3816 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/268a6e5a/ql/src/test/results/clientpositive/groupby3_noskew.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby3_noskew.q.out b/ql/src/test/results/clientpositive/groupby3_noskew.q.out
index 075f7c7..71a9d20 100644
--- a/ql/src/test/results/clientpositive/groupby3_noskew.q.out
+++ b/ql/src/test/results/clientpositive/groupby3_noskew.q.out
@@ -47,15 +47,15 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: substr(value, 5) (type: string), UDFToDouble(substr(value, 5)) (type: double), (UDFToDouble(substr(value, 5)) * UDFToDouble(substr(value, 5))) (type: double)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: double), _col1 (type: double)
Execution mode: vectorized
Reduce Operator Tree:
@@ -63,14 +63,14 @@ STAGE PLANS:
aggregations: sum(KEY._col0:0._col0), count(KEY._col0:0._col0), sum(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), max(KEY._col0:0._col0), min(KEY._col0:0._col0), sum(VALUE._col0), sum(VALUE._col1)
mode: complete
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
- Statistics: Num rows: 1 Data size: 416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 416 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: double), (_col0 / _col1) (type: double), (_col2 / _col3) (type: double), UDFToDouble(_col4) (type: double), UDFToDouble(_col5) (type: double), power(((_col6 - ((_col7 * _col7) / _col1)) / _col1), 0.5) (type: double), power(((_col6 - ((_col7 * _col7) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END), 0.5) (type: double), ((_col6 - ((_col7 * _col7) / _col1)) / _col1) (type: double), ((_col6 - ((_col7 * _col7) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 1 Data size: 416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -79,15 +79,15 @@ STAGE PLANS:
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)
outputColumnNames: c1, c2, c3, c4, c5, c6, c7, c8, c9
- Statistics: Num rows: 1 Data size: 416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
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')
mode: complete
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 1 Data size: 4128 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 3960 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 4128 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 3960 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/268a6e5a/ql/src/test/results/clientpositive/groupby3_noskew_multi_distinct.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby3_noskew_multi_distinct.q.out b/ql/src/test/results/clientpositive/groupby3_noskew_multi_distinct.q.out
index a662e22..032e752 100644
--- a/ql/src/test/results/clientpositive/groupby3_noskew_multi_distinct.q.out
+++ b/ql/src/test/results/clientpositive/groupby3_noskew_multi_distinct.q.out
@@ -51,15 +51,15 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: substr(value, 5) (type: string), UDFToDouble(substr(value, 5)) (type: double), (UDFToDouble(substr(value, 5)) * UDFToDouble(substr(value, 5))) (type: double)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: double), _col1 (type: double)
Execution mode: vectorized
Reduce Operator Tree:
@@ -67,14 +67,14 @@ STAGE PLANS:
aggregations: sum(KEY._col0:0._col0), count(KEY._col0:0._col0), sum(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), max(KEY._col0:0._col0), min(KEY._col0:0._col0), sum(VALUE._col0), sum(VALUE._col1)
mode: complete
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
- Statistics: Num rows: 1 Data size: 416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 416 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: double), (_col0 / _col1) (type: double), (_col2 / _col3) (type: double), UDFToDouble(_col4) (type: double), UDFToDouble(_col5) (type: double), power(((_col6 - ((_col7 * _col7) / _col1)) / _col1), 0.5) (type: double), power(((_col6 - ((_col7 * _col7) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END), 0.5) (type: double), ((_col6 - ((_col7 * _col7) / _col1)) / _col1) (type: double), ((_col6 - ((_col7 * _col7) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END) (type: double), _col2 (type: double), UDFToDouble(_col3) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
- Statistics: Num rows: 1 Data size: 416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -83,15 +83,15 @@ STAGE PLANS:
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: 416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
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: 5008 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 4840 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 5008 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 4840 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/268a6e5a/ql/src/test/results/clientpositive/groupby4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby4.q.out b/ql/src/test/results/clientpositive/groupby4.q.out
index 9421907..9f5076b 100644
--- a/ql/src/test/results/clientpositive/groupby4.q.out
+++ b/ql/src/test/results/clientpositive/groupby4.q.out
@@ -32,23 +32,23 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: substr(key, 1, 1) (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: rand() (type: double)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: string)
mode: partial1
outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -64,17 +64,17 @@ STAGE PLANS:
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: string)
mode: final
outputColumnNames: _col0
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 58144 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 58144 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -83,7 +83,7 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string)
outputColumnNames: c1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 58144 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -116,7 +116,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Map-reduce partition columns: rand() (type: double)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 58144 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: c1 (type: string)
Execution mode: vectorized
Reduce Operator Tree:
@@ -124,7 +124,7 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0, 'hll')
mode: partial1
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -138,7 +138,7 @@ STAGE PLANS:
TableScan
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
Execution mode: vectorized
Reduce Operator Tree:
@@ -146,10 +146,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0)
mode: final
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 440 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/268a6e5a/ql/src/test/results/clientpositive/groupby4_noskew.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby4_noskew.q.out b/ql/src/test/results/clientpositive/groupby4_noskew.q.out
index 6ec0204..e5177f2 100644
--- a/ql/src/test/results/clientpositive/groupby4_noskew.q.out
+++ b/ql/src/test/results/clientpositive/groupby4_noskew.q.out
@@ -30,26 +30,26 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: substr(key, 1, 1) (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: string)
mode: complete
outputColumnNames: _col0
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 58144 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 58144 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -58,7 +58,7 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string)
outputColumnNames: c1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 58144 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -90,7 +90,7 @@ STAGE PLANS:
TableScan
Reduce Output Operator
sort order:
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 58144 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: c1 (type: string)
Execution mode: vectorized
Reduce Operator Tree:
@@ -98,10 +98,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0, 'hll')
mode: complete
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat