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 16:38:49 UTC
[17/51] [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/groupby9.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby9.q.out b/ql/src/test/results/clientpositive/groupby9.q.out
index 750075c..ea97956 100644
--- a/ql/src/test/results/clientpositive/groupby9.q.out
+++ b/ql/src/test/results/clientpositive/groupby9.q.out
@@ -46,32 +46,32 @@ 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), value (type: string), substr(value, 5) (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: 500 Data size: 185000 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -84,14 +84,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ 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
@@ -100,12 +100,12 @@ 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:
@@ -137,7 +137,7 @@ 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:
@@ -145,10 +145,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
mode: mergepartial
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
@@ -170,7 +170,7 @@ STAGE PLANS:
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
sort order: +++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 185000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
@@ -178,14 +178,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), CAST( _col2 AS STRING) (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 139500 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: 500 Data size: 139500 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -194,12 +194,12 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string)
outputColumnNames: key, val1, val2
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 139500 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: compute_stats(key, 'hll'), compute_stats(val1, 'hll'), compute_stats(val2, '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:
@@ -223,7 +223,7 @@ 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,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
Execution mode: vectorized
Reduce Operator Tree:
@@ -231,10 +231,10 @@ 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
@@ -925,32 +925,32 @@ 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: value (type: string), key (type: string), substr(value, 5) (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: 500 Data size: 185000 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -963,14 +963,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ 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
@@ -979,12 +979,12 @@ 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:
@@ -1016,7 +1016,7 @@ 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:
@@ -1024,10 +1024,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
mode: mergepartial
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
@@ -1049,7 +1049,7 @@ STAGE PLANS:
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
sort order: +++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 185000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
@@ -1057,14 +1057,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: UDFToInteger(_col1) (type: int), _col0 (type: string), CAST( _col2 AS STRING) (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 139500 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: 500 Data size: 139500 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -1073,12 +1073,12 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string)
outputColumnNames: key, val1, val2
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 139500 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: compute_stats(key, 'hll'), compute_stats(val1, 'hll'), compute_stats(val2, '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:
@@ -1102,7 +1102,7 @@ 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,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
Execution mode: vectorized
Reduce Operator Tree:
@@ -1110,10 +1110,10 @@ 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
@@ -1804,32 +1804,32 @@ 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), value (type: string), substr(value, 5) (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: 500 Data size: 185000 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -1842,14 +1842,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ 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
@@ -1858,12 +1858,12 @@ 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:
@@ -1895,7 +1895,7 @@ 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:
@@ -1903,10 +1903,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
mode: mergepartial
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
@@ -1928,7 +1928,7 @@ STAGE PLANS:
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
sort order: +++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 185000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
@@ -1936,14 +1936,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), CAST( _col2 AS STRING) (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 139500 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: 500 Data size: 139500 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -1952,12 +1952,12 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string)
outputColumnNames: key, val1, val2
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 139500 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: compute_stats(key, 'hll'), compute_stats(val1, 'hll'), compute_stats(val2, '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:
@@ -1981,7 +1981,7 @@ 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,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
Execution mode: vectorized
Reduce Operator Tree:
@@ -1989,10 +1989,10 @@ 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
@@ -2683,33 +2683,33 @@ 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
Group By Operator
aggregations: count(substr(value, 5))
keys: key (type: string)
mode: hash
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
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: 23750 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
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(substr(value, 5))
keys: key (type: string), value (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: 46500 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -2723,14 +2723,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ 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
@@ -2739,12 +2739,12 @@ 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: 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:
@@ -2776,7 +2776,7 @@ 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:
@@ -2784,10 +2784,10 @@ 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
@@ -2809,7 +2809,7 @@ STAGE PLANS:
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: bigint)
Execution mode: vectorized
Reduce Operator Tree:
@@ -2818,14 +2818,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (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: 46500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), CAST( _col2 AS STRING) (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: 69750 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: 69750 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -2834,12 +2834,12 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string)
outputColumnNames: key, val1, val2
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 69750 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: compute_stats(key, 'hll'), compute_stats(val1, 'hll'), compute_stats(val2, 'hll')
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 1304 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:
@@ -2863,7 +2863,7 @@ STAGE PLANS:
TableScan
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 1304 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,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
Execution mode: vectorized
Reduce Operator Tree:
@@ -2871,10 +2871,10 @@ 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: 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
@@ -3565,32 +3565,32 @@ 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: value (type: string), key (type: string), substr(value, 5) (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: 500 Data size: 185000 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -3603,14 +3603,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ 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
@@ -3619,12 +3619,12 @@ 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:
@@ -3656,7 +3656,7 @@ 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:
@@ -3664,10 +3664,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
mode: mergepartial
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
@@ -3689,7 +3689,7 @@ STAGE PLANS:
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
sort order: +++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 185000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
@@ -3697,14 +3697,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: UDFToInteger(_col1) (type: int), _col0 (type: string), CAST( _col2 AS STRING) (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 139500 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: 500 Data size: 139500 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -3713,12 +3713,12 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string)
outputColumnNames: key, val1, val2
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 139500 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: compute_stats(key, 'hll'), compute_stats(val1, 'hll'), compute_stats(val2, '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:
@@ -3742,7 +3742,7 @@ 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,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
Execution mode: vectorized
Reduce Operator Tree:
@@ -3750,10 +3750,10 @@ 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/groupby_complex_types.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby_complex_types.q.out b/ql/src/test/results/clientpositive/groupby_complex_types.q.out
index 5d4eb7c..93161af 100644
--- a/ql/src/test/results/clientpositive/groupby_complex_types.q.out
+++ b/ql/src/test/results/clientpositive/groupby_complex_types.q.out
@@ -59,33 +59,33 @@ 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)
outputColumnNames: key
- 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(1)
keys: array(key) (type: array<string>)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 482000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: array<string>)
sort order: +
Map-reduce partition columns: _col0 (type: array<string>)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 482000 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
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(1)
keys: map(key:value) (type: map<string,string>)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 232000 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -95,13 +95,13 @@ STAGE PLANS:
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(1)
keys: struct(key,value) (type: struct<col1:string,col2:string>)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 106000 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -114,10 +114,10 @@ STAGE PLANS:
keys: KEY._col0 (type: array<string>)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 482000 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: 482000 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -146,7 +146,7 @@ STAGE PLANS:
key expressions: _col0 (type: map<string,string>)
sort order: +
Map-reduce partition columns: _col0 (type: map<string,string>)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 232000 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Execution mode: vectorized
Reduce Operator Tree:
@@ -155,10 +155,10 @@ STAGE PLANS:
keys: KEY._col0 (type: map<string,string>)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 232000 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: 232000 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -187,7 +187,7 @@ STAGE PLANS:
key expressions: _col0 (type: struct<col1:string,col2:string>)
sort order: +
Map-reduce partition columns: _col0 (type: struct<col1:string,col2:string>)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 106000 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Execution mode: vectorized
Reduce Operator Tree:
@@ -196,10 +196,10 @@ STAGE PLANS:
keys: KEY._col0 (type: struct<col1:string,col2:string>)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 106000 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: 106000 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/268a6e5a/ql/src/test/results/clientpositive/groupby_complex_types_multi_single_reducer.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby_complex_types_multi_single_reducer.q.out b/ql/src/test/results/clientpositive/groupby_complex_types_multi_single_reducer.q.out
index fcb12ee..b577d4e 100644
--- a/ql/src/test/results/clientpositive/groupby_complex_types_multi_single_reducer.q.out
+++ b/ql/src/test/results/clientpositive/groupby_complex_types_multi_single_reducer.q.out
@@ -46,34 +46,34 @@ 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)
outputColumnNames: key
- 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(1)
keys: array(key) (type: array<string>)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 482000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: array<string>)
sort order: +
Map-reduce partition columns: _col0 (type: array<string>)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 482000 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
value expressions: _col1 (type: bigint)
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(1)
keys: map(key:value) (type: map<string,string>)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 232000 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -86,7 +86,7 @@ STAGE PLANS:
keys: KEY._col0 (type: array<string>)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 482000 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -101,7 +101,7 @@ STAGE PLANS:
Reduce Output Operator
key expressions: _col0 (type: array<string>)
sort order: +
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 482000 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
value expressions: _col1 (type: bigint)
Execution mode: vectorized
@@ -109,13 +109,13 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: array<string>), VALUE._col0 (type: bigint)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 482000 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: 19280 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 19280 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -144,7 +144,7 @@ STAGE PLANS:
key expressions: _col0 (type: map<string,string>)
sort order: +
Map-reduce partition columns: _col0 (type: map<string,string>)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 232000 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
value expressions: _col1 (type: bigint)
Execution mode: vectorized
@@ -154,7 +154,7 @@ STAGE PLANS:
keys: KEY._col0 (type: map<string,string>)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 232000 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -169,7 +169,7 @@ STAGE PLANS:
Reduce Output Operator
key expressions: _col0 (type: map<string,string>)
sort order: +
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 232000 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
value expressions: _col1 (type: bigint)
Execution mode: vectorized
@@ -177,13 +177,13 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: map<string,string>), VALUE._col0 (type: bigint)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 232000 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: 9280 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 9280 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat