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 16:38:50 UTC
[18/51] [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/groupby7_noskew_multi_single_reducer.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby7_noskew_multi_single_reducer.q.out b/ql/src/test/results/clientpositive/groupby7_noskew_multi_single_reducer.q.out
index 325f638..3e94d1a 100644
--- a/ql/src/test/results/clientpositive/groupby7_noskew_multi_single_reducer.q.out
+++ b/ql/src/test/results/clientpositive/groupby7_noskew_multi_single_reducer.q.out
@@ -47,27 +47,27 @@ 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: key (type: string), value (type: string)
outputColumnNames: key, value
- 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: key (type: string)
sort order: +
Map-reduce partition columns: key (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: substr(value, 5) (type: string)
Execution mode: vectorized
Reduce Operator Tree:
Forward
- 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: sum(VALUE._col0)
keys: KEY._col0 (type: string)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: true
table:
@@ -79,7 +79,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: true
table:
@@ -94,7 +94,7 @@ STAGE PLANS:
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
value expressions: _col1 (type: double)
Execution mode: vectorized
@@ -102,17 +102,17 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: double)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE
Limit
Number of rows: 10
- Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: true
- Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -121,7 +121,7 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: int), _col1 (type: string)
outputColumnNames: key, value
- Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: true
table:
@@ -153,7 +153,7 @@ STAGE PLANS:
TableScan
Reduce Output Operator
sort order:
- Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: key (type: int), value (type: string)
Execution mode: vectorized
Reduce Operator Tree:
@@ -161,10 +161,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll')
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: true
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -185,7 +185,7 @@ STAGE PLANS:
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
value expressions: _col1 (type: double)
Execution mode: vectorized
@@ -193,17 +193,17 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: double)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE
Limit
Number of rows: 10
- Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: true
- Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -212,7 +212,7 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: int), _col1 (type: string)
outputColumnNames: key, value
- Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: true
table:
@@ -236,7 +236,7 @@ STAGE PLANS:
TableScan
Reduce Output Operator
sort order:
- Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: key (type: int), value (type: string)
Execution mode: vectorized
Reduce Operator Tree:
@@ -244,10 +244,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll')
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: true
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 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/groupby8.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby8.q.out b/ql/src/test/results/clientpositive/groupby8.q.out
index aa373a9..b5e234a 100644
--- a/ql/src/test/results/clientpositive/groupby8.q.out
+++ b/ql/src/test/results/clientpositive/groupby8.q.out
@@ -50,20 +50,20 @@ 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: key (type: string), value (type: string)
outputColumnNames: key, value
- 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: key (type: string), substr(value, 5) (type: string)
sort order: ++
Map-reduce partition columns: key (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
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: key, value
- 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
File Output Operator
compressed: false
table:
@@ -77,7 +77,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: partial1
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -93,7 +93,7 @@ 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: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Execution mode: vectorized
Reduce Operator Tree:
@@ -102,14 +102,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: final
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 59408 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: 59408 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -118,7 +118,7 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: int), _col1 (type: string)
outputColumnNames: key, value
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -151,7 +151,7 @@ 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: 59408 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: key (type: int), value (type: string)
Execution mode: vectorized
Reduce Operator Tree:
@@ -159,7 +159,7 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll')
mode: partial1
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -173,7 +173,7 @@ STAGE PLANS:
TableScan
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
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>)
Execution mode: vectorized
Reduce Operator Tree:
@@ -181,10 +181,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
mode: final
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -206,7 +206,7 @@ STAGE PLANS:
key expressions: key (type: string), substr(value, 5) (type: string)
sort order: ++
Map-reduce partition columns: key (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
@@ -214,7 +214,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: partial1
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -230,7 +230,7 @@ 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: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Execution mode: vectorized
Reduce Operator Tree:
@@ -239,14 +239,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: final
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 59408 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: 59408 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -255,7 +255,7 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: int), _col1 (type: string)
outputColumnNames: key, value
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -280,7 +280,7 @@ 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: 59408 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: key (type: int), value (type: string)
Execution mode: vectorized
Reduce Operator Tree:
@@ -288,7 +288,7 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll')
mode: partial1
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -302,7 +302,7 @@ STAGE PLANS:
TableScan
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
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>)
Execution mode: vectorized
Reduce Operator Tree:
@@ -310,10 +310,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
mode: final
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1007,20 +1007,20 @@ 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: key (type: string), value (type: string)
outputColumnNames: key, value
- 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: key (type: string), substr(value, 5) (type: string)
sort order: ++
Map-reduce partition columns: key (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
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: key, value
- 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
File Output Operator
compressed: false
table:
@@ -1034,7 +1034,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: partial1
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -1050,7 +1050,7 @@ 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: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Execution mode: vectorized
Reduce Operator Tree:
@@ -1059,14 +1059,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: final
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 59408 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: 59408 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -1075,7 +1075,7 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: int), _col1 (type: string)
outputColumnNames: key, value
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -1108,7 +1108,7 @@ 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: 59408 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: key (type: int), value (type: string)
Execution mode: vectorized
Reduce Operator Tree:
@@ -1116,7 +1116,7 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll')
mode: partial1
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -1130,7 +1130,7 @@ STAGE PLANS:
TableScan
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
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>)
Execution mode: vectorized
Reduce Operator Tree:
@@ -1138,10 +1138,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
mode: final
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1163,7 +1163,7 @@ STAGE PLANS:
key expressions: key (type: string), substr(value, 5) (type: string)
sort order: ++
Map-reduce partition columns: key (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
@@ -1171,7 +1171,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: partial1
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -1187,7 +1187,7 @@ 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: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Execution mode: vectorized
Reduce Operator Tree:
@@ -1196,14 +1196,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: final
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 59408 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: 59408 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -1212,7 +1212,7 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: int), _col1 (type: string)
outputColumnNames: key, value
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -1237,7 +1237,7 @@ 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: 59408 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: key (type: int), value (type: string)
Execution mode: vectorized
Reduce Operator Tree:
@@ -1245,7 +1245,7 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll')
mode: partial1
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -1259,7 +1259,7 @@ STAGE PLANS:
TableScan
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
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>)
Execution mode: vectorized
Reduce Operator Tree:
@@ -1267,10 +1267,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
mode: final
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 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/groupby8_map.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby8_map.q.out b/ql/src/test/results/clientpositive/groupby8_map.q.out
index b2abd59..d5864ac 100644
--- a/ql/src/test/results/clientpositive/groupby8_map.q.out
+++ b/ql/src/test/results/clientpositive/groupby8_map.q.out
@@ -45,33 +45,33 @@ 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: key (type: string), value (type: string)
outputColumnNames: key, value
- 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: key (type: string), substr(value, 5) (type: string)
sort order: ++
Map-reduce partition columns: key (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:
Forward
- 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 KEY._col1:0._col0)
keys: KEY._col0 (type: string)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 59408 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: 59408 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -80,12 +80,12 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: int), _col1 (type: string)
outputColumnNames: key, value
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE
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
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -97,14 +97,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 59408 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: 59408 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -113,12 +113,12 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: int), _col1 (type: string)
outputColumnNames: key, value
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE
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
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -150,7 +150,7 @@ STAGE PLANS:
TableScan
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
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>)
Execution mode: vectorized
Reduce Operator Tree:
@@ -158,10 +158,10 @@ STAGE PLANS:
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
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -191,7 +191,7 @@ STAGE PLANS:
TableScan
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
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>)
Execution mode: vectorized
Reduce Operator Tree:
@@ -199,10 +199,10 @@ STAGE PLANS:
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
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 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/groupby8_map_skew.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby8_map_skew.q.out b/ql/src/test/results/clientpositive/groupby8_map_skew.q.out
index 4e7341e..098023e 100644
--- a/ql/src/test/results/clientpositive/groupby8_map_skew.q.out
+++ b/ql/src/test/results/clientpositive/groupby8_map_skew.q.out
@@ -48,32 +48,32 @@ 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: key (type: string), value (type: string)
outputColumnNames: key, value
- 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 substr(value, 5))
keys: key (type: string), substr(value, 5) (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 69750 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: 69750 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: key, value
- 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 substr(value, 5))
keys: key (type: string), substr(value, 5) (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 69750 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -86,7 +86,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: partials
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -102,7 +102,7 @@ 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: 23750 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Execution mode: vectorized
Reduce Operator Tree:
@@ -111,14 +111,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: final
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 47000 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: 47000 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -127,12 +127,12 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: int), _col1 (type: string)
outputColumnNames: key, value
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 47000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 872 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -164,7 +164,7 @@ STAGE PLANS:
TableScan
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 872 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
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>)
Execution mode: vectorized
Reduce Operator Tree:
@@ -172,10 +172,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
mode: final
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -197,7 +197,7 @@ STAGE PLANS:
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: 69750 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
@@ -205,7 +205,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: partials
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -221,7 +221,7 @@ 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: 23750 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Execution mode: vectorized
Reduce Operator Tree:
@@ -230,14 +230,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: final
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 47000 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: 47000 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -246,12 +246,12 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: int), _col1 (type: string)
outputColumnNames: key, value
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 47000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 872 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -275,7 +275,7 @@ STAGE PLANS:
TableScan
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 872 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
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>)
Execution mode: vectorized
Reduce Operator Tree:
@@ -283,10 +283,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
mode: final
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 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/groupby8_noskew.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby8_noskew.q.out b/ql/src/test/results/clientpositive/groupby8_noskew.q.out
index 1d9b461..0563c7f 100644
--- a/ql/src/test/results/clientpositive/groupby8_noskew.q.out
+++ b/ql/src/test/results/clientpositive/groupby8_noskew.q.out
@@ -45,33 +45,33 @@ 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: key (type: string), value (type: string)
outputColumnNames: key, value
- 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: key (type: string), substr(value, 5) (type: string)
sort order: ++
Map-reduce partition columns: key (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:
Forward
- 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 KEY._col1:0._col0)
keys: KEY._col0 (type: string)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 59408 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: 59408 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -80,7 +80,7 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: int), _col1 (type: string)
outputColumnNames: key, value
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -92,14 +92,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 59408 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: 59408 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -108,7 +108,7 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: int), _col1 (type: string)
outputColumnNames: key, value
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -140,7 +140,7 @@ 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: 59408 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: key (type: int), value (type: string)
Execution mode: vectorized
Reduce Operator Tree:
@@ -148,10 +148,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll')
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -181,7 +181,7 @@ 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: 59408 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: key (type: int), value (type: string)
Execution mode: vectorized
Reduce Operator Tree:
@@ -189,10 +189,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll')
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat