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 16:38:51 UTC
[19/51] [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/groupby5.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby5.q.out b/ql/src/test/results/clientpositive/groupby5.q.out
index 7944a8f..f29a1e5 100644
--- a/ql/src/test/results/clientpositive/groupby5.q.out
+++ b/ql/src/test/results/clientpositive/groupby5.q.out
@@ -36,16 +36,16 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), substr(value, 5) (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: rand() (type: double)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: string)
Execution mode: vectorized
Reduce Operator Tree:
@@ -54,7 +54,7 @@ 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:
@@ -70,7 +70,7 @@ STAGE PLANS:
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: double)
Execution mode: vectorized
Reduce Operator Tree:
@@ -79,14 +79,14 @@ 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
@@ -95,7 +95,7 @@ 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:
@@ -128,7 +128,7 @@ 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:
@@ -136,7 +136,7 @@ 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:
@@ -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: 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/groupby5_map.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby5_map.q.out b/ql/src/test/results/clientpositive/groupby5_map.q.out
index 499986f..b26e6da 100644
--- a/ql/src/test/results/clientpositive/groupby5_map.q.out
+++ b/ql/src/test/results/clientpositive/groupby5_map.q.out
@@ -27,33 +27,33 @@ 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: 43500 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: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(key)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: double)
Reduce Operator Tree:
Group By Operator
aggregations: sum(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: UDFToInteger(_col0) (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -62,19 +62,19 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: int)
outputColumnNames: key
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: compute_stats(key, 'hll')
mode: complete
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 424 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/groupby5_map_skew.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby5_map_skew.q.out b/ql/src/test/results/clientpositive/groupby5_map_skew.q.out
index f5ddd19..69f553c 100644
--- a/ql/src/test/results/clientpositive/groupby5_map_skew.q.out
+++ b/ql/src/test/results/clientpositive/groupby5_map_skew.q.out
@@ -27,33 +27,33 @@ 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: 43500 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: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(key)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: double)
Reduce Operator Tree:
Group By Operator
aggregations: sum(VALUE._col0)
mode: final
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: UDFToInteger(_col0) (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -62,19 +62,19 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: int)
outputColumnNames: key
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: compute_stats(key, 'hll')
mode: complete
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 424 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/groupby5_noskew.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby5_noskew.q.out b/ql/src/test/results/clientpositive/groupby5_noskew.q.out
index 5cdd89f..64b6b94 100644
--- a/ql/src/test/results/clientpositive/groupby5_noskew.q.out
+++ b/ql/src/test/results/clientpositive/groupby5_noskew.q.out
@@ -34,16 +34,16 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), substr(value, 5) (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: string)
Execution mode: vectorized
Reduce Operator Tree:
@@ -52,14 +52,14 @@ 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
@@ -68,7 +68,7 @@ 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:
@@ -100,7 +100,7 @@ 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:
@@ -108,10 +108,10 @@ 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
http://git-wip-us.apache.org/repos/asf/hive/blob/268a6e5a/ql/src/test/results/clientpositive/groupby6.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby6.q.out b/ql/src/test/results/clientpositive/groupby6.q.out
index 0b58c94..7ecebf6 100644
--- a/ql/src/test/results/clientpositive/groupby6.q.out
+++ b/ql/src/test/results/clientpositive/groupby6.q.out
@@ -32,23 +32,23 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: substr(value, 5, 1) (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: rand() (type: double)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: string)
mode: partial1
outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -64,17 +64,17 @@ STAGE PLANS:
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: string)
mode: final
outputColumnNames: _col0
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 307 Data size: 56488 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: 307 Data size: 56488 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -83,7 +83,7 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string)
outputColumnNames: c1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 307 Data size: 56488 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -116,7 +116,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Map-reduce partition columns: rand() (type: double)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 307 Data size: 56488 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: c1 (type: string)
Execution mode: vectorized
Reduce Operator Tree:
@@ -124,7 +124,7 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0, 'hll')
mode: partial1
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -138,7 +138,7 @@ STAGE PLANS:
TableScan
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
Execution mode: vectorized
Reduce Operator Tree:
@@ -146,10 +146,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0)
mode: final
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/268a6e5a/ql/src/test/results/clientpositive/groupby6_map.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby6_map.q.out b/ql/src/test/results/clientpositive/groupby6_map.q.out
index a2fee3f..50370db 100644
--- a/ql/src/test/results/clientpositive/groupby6_map.q.out
+++ b/ql/src/test/results/clientpositive/groupby6_map.q.out
@@ -30,31 +30,31 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: substr(value, 5, 1) (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 46000 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: 46000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 46000 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: 46000 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -63,12 +63,12 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string)
outputColumnNames: c1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 46000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: compute_stats(c1, 'hll')
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -100,7 +100,7 @@ STAGE PLANS:
TableScan
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
Execution mode: vectorized
Reduce Operator Tree:
@@ -108,10 +108,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/268a6e5a/ql/src/test/results/clientpositive/groupby6_map_skew.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby6_map_skew.q.out b/ql/src/test/results/clientpositive/groupby6_map_skew.q.out
index 0cac232..a1124b3 100644
--- a/ql/src/test/results/clientpositive/groupby6_map_skew.q.out
+++ b/ql/src/test/results/clientpositive/groupby6_map_skew.q.out
@@ -31,28 +31,28 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: substr(value, 5, 1) (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 46000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: rand() (type: double)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 46000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: string)
mode: partials
outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 46000 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -68,17 +68,17 @@ STAGE PLANS:
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 46000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: string)
mode: final
outputColumnNames: _col0
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 46000 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: 46000 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -87,12 +87,12 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string)
outputColumnNames: c1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 46000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: compute_stats(c1, 'hll')
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -124,7 +124,7 @@ STAGE PLANS:
TableScan
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
Execution mode: vectorized
Reduce Operator Tree:
@@ -132,10 +132,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0)
mode: final
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/268a6e5a/ql/src/test/results/clientpositive/groupby6_noskew.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby6_noskew.q.out b/ql/src/test/results/clientpositive/groupby6_noskew.q.out
index 4504b53..5a68c75 100644
--- a/ql/src/test/results/clientpositive/groupby6_noskew.q.out
+++ b/ql/src/test/results/clientpositive/groupby6_noskew.q.out
@@ -30,26 +30,26 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: substr(value, 5, 1) (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
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: 45500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: string)
mode: complete
outputColumnNames: _col0
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 307 Data size: 56488 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: 307 Data size: 56488 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -58,7 +58,7 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string)
outputColumnNames: c1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 307 Data size: 56488 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -90,7 +90,7 @@ STAGE PLANS:
TableScan
Reduce Output Operator
sort order:
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 307 Data size: 56488 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: c1 (type: string)
Execution mode: vectorized
Reduce Operator Tree:
@@ -98,10 +98,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0, 'hll')
mode: complete
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/268a6e5a/ql/src/test/results/clientpositive/groupby7_map.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby7_map.q.out b/ql/src/test/results/clientpositive/groupby7_map.q.out
index 940533c..fe67667 100644
--- a/ql/src/test/results/clientpositive/groupby7_map.q.out
+++ b/ql/src/test/results/clientpositive/groupby7_map.q.out
@@ -46,33 +46,33 @@ 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: sum(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: double)
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: sum(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
File Output Operator
compressed: true
table:
@@ -85,14 +85,14 @@ 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: true
- 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
@@ -101,12 +101,12 @@ 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: true
table:
@@ -138,7 +138,7 @@ 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:
@@ -146,10 +146,10 @@ 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: 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
@@ -171,7 +171,7 @@ 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: double)
Execution mode: vectorized
Reduce Operator Tree:
@@ -180,14 +180,14 @@ 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: true
- 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
@@ -196,12 +196,12 @@ 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: true
table:
@@ -225,7 +225,7 @@ 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:
@@ -233,10 +233,10 @@ 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: 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/groupby7_map_multi_single_reducer.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby7_map_multi_single_reducer.q.out b/ql/src/test/results/clientpositive/groupby7_map_multi_single_reducer.q.out
index 973e408..ee11ebc 100644
--- a/ql/src/test/results/clientpositive/groupby7_map_multi_single_reducer.q.out
+++ b/ql/src/test/results/clientpositive/groupby7_map_multi_single_reducer.q.out
@@ -45,34 +45,34 @@ 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), 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
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: true
- 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
@@ -81,12 +81,12 @@ 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: true
table:
@@ -98,14 +98,14 @@ 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: true
- 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
@@ -114,12 +114,12 @@ 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: true
table:
@@ -151,7 +151,7 @@ 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:
@@ -159,10 +159,10 @@ 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: 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
@@ -192,7 +192,7 @@ 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:
@@ -200,10 +200,10 @@ 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: 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/groupby7_map_skew.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby7_map_skew.q.out b/ql/src/test/results/clientpositive/groupby7_map_skew.q.out
index 5a6d326..f6339e3 100644
--- a/ql/src/test/results/clientpositive/groupby7_map_skew.q.out
+++ b/ql/src/test/results/clientpositive/groupby7_map_skew.q.out
@@ -48,33 +48,33 @@ 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: sum(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: rand() (type: double)
- 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: double)
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: sum(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
File Output Operator
compressed: true
table:
@@ -87,7 +87,7 @@ 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: true
table:
@@ -103,7 +103,7 @@ 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: double)
Execution mode: vectorized
Reduce Operator Tree:
@@ -112,14 +112,14 @@ 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: true
- 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
@@ -128,12 +128,12 @@ 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: true
table:
@@ -165,7 +165,7 @@ 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:
@@ -173,10 +173,10 @@ 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: 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
@@ -198,7 +198,7 @@ STAGE PLANS:
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: rand() (type: double)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: double)
Execution mode: vectorized
Reduce Operator Tree:
@@ -207,7 +207,7 @@ 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: true
table:
@@ -223,7 +223,7 @@ 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: double)
Execution mode: vectorized
Reduce Operator Tree:
@@ -232,14 +232,14 @@ 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: true
- 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
@@ -248,12 +248,12 @@ 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: true
table:
@@ -277,7 +277,7 @@ 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:
@@ -285,10 +285,10 @@ 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: 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/groupby7_noskew.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby7_noskew.q.out b/ql/src/test/results/clientpositive/groupby7_noskew.q.out
index 00895ca..99e24a8 100644
--- a/ql/src/test/results/clientpositive/groupby7_noskew.q.out
+++ b/ql/src/test/results/clientpositive/groupby7_noskew.q.out
@@ -46,21 +46,21 @@ 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)
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: true
table:
@@ -74,14 +74,14 @@ 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: true
- 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
@@ -90,7 +90,7 @@ 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: true
table:
@@ -122,7 +122,7 @@ 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:
@@ -130,10 +130,10 @@ 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
@@ -155,7 +155,7 @@ STAGE PLANS:
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:
@@ -164,14 +164,14 @@ 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: true
- 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
@@ -180,7 +180,7 @@ 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: true
table:
@@ -204,7 +204,7 @@ 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:
@@ -212,10 +212,10 @@ 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