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 2017/12/20 10:40:11 UTC
[10/37] hive git commit: HIVE-18149: Stats: rownum estimation from
datasize underestimates in most cases (Zoltan Haindrich,
reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/e26b9325/ql/src/test/results/clientpositive/spark/spark_dynamic_partition_pruning_2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/spark_dynamic_partition_pruning_2.q.out b/ql/src/test/results/clientpositive/spark/spark_dynamic_partition_pruning_2.q.out
index 075aaff..2049018 100644
--- a/ql/src/test/results/clientpositive/spark/spark_dynamic_partition_pruning_2.q.out
+++ b/ql/src/test/results/clientpositive/spark/spark_dynamic_partition_pruning_2.q.out
@@ -500,11 +500,11 @@ STAGE PLANS:
TableScan
alias: agg
filterExpr: dim_shops_id is not null (type: boolean)
- Statistics: Num rows: 9 Data size: 27 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 270 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: dim_shops_id (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 9 Data size: 27 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 270 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
Inner Join 0 to 1
@@ -514,14 +514,14 @@ STAGE PLANS:
outputColumnNames: _col2
input vertices:
1 Map 2
- Statistics: Num rows: 9 Data size: 29 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 297 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col2 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 9 Data size: 29 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 297 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 9 Data size: 29 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 297 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1054,11 +1054,11 @@ STAGE PLANS:
TableScan
alias: s2
filterExpr: ds is not null (type: boolean)
- Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2000 Data size: 212480 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ds (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2000 Data size: 212480 Basic stats: COMPLETE Column stats: NONE
Spark HashTable Sink Operator
keys:
0 _col0 (type: string)
@@ -1077,11 +1077,11 @@ STAGE PLANS:
TableScan
alias: s1
filterExpr: ds is not null (type: boolean)
- Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2000 Data size: 212480 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ds (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2000 Data size: 212480 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
Inner Join 0 to 1
@@ -1090,7 +1090,7 @@ STAGE PLANS:
1 _col0 (type: string)
input vertices:
1 Map 3
- Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2200 Data size: 233728 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
mode: hash
http://git-wip-us.apache.org/repos/asf/hive/blob/e26b9325/ql/src/test/results/clientpositive/spark/spark_dynamic_partition_pruning_4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/spark_dynamic_partition_pruning_4.q.out b/ql/src/test/results/clientpositive/spark/spark_dynamic_partition_pruning_4.q.out
index a06c3e3..85a7c79 100644
--- a/ql/src/test/results/clientpositive/spark/spark_dynamic_partition_pruning_4.q.out
+++ b/ql/src/test/results/clientpositive/spark/spark_dynamic_partition_pruning_4.q.out
@@ -2019,12 +2019,12 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: part2
- Statistics: Num rows: 8 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8 Data size: 240 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: p (type: string)
sort order: +
Map-reduce partition columns: p (type: string)
- Statistics: Num rows: 8 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8 Data size: 240 Basic stats: COMPLETE Column stats: NONE
Map 3
Map Operator Tree:
TableScan
@@ -2047,12 +2047,12 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: part1
- Statistics: Num rows: 8 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8 Data size: 240 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: p (type: string)
sort order: +
Map-reduce partition columns: p (type: string)
- Statistics: Num rows: 8 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8 Data size: 240 Basic stats: COMPLETE Column stats: NONE
Map 9
Map Operator Tree:
TableScan
@@ -2097,14 +2097,14 @@ STAGE PLANS:
condition map:
Left Semi Join 0 to 1
outputColumnNames: _col2
- Statistics: Num rows: 8 Data size: 26 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8 Data size: 264 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col2 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 8 Data size: 26 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8 Data size: 264 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 16 Data size: 52 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 16 Data size: 528 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2135,14 +2135,14 @@ STAGE PLANS:
condition map:
Left Semi Join 0 to 1
outputColumnNames: _col2
- Statistics: Num rows: 8 Data size: 26 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8 Data size: 264 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col2 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 8 Data size: 26 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8 Data size: 264 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 16 Data size: 52 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 16 Data size: 528 Basic stats: COMPLETE Column stats: NONE
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/e26b9325/ql/src/test/results/clientpositive/spark/spark_explainuser_1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/spark_explainuser_1.q.out b/ql/src/test/results/clientpositive/spark/spark_explainuser_1.q.out
index 810e7b2..257d316 100644
--- a/ql/src/test/results/clientpositive/spark/spark_explainuser_1.q.out
+++ b/ql/src/test/results/clientpositive/spark/spark_explainuser_1.q.out
@@ -166,8 +166,8 @@ Stage-0
GROUP [RS_4]
Group By Operator [GBY_3] (rows=1 width=8)
Output:["_col0"],aggregations:["count()"]
- Select Operator [SEL_2] (rows=500 width=94)
- TableScan [TS_0] (rows=500 width=94)
+ Select Operator [SEL_2] (rows=500 width=940)
+ TableScan [TS_0] (rows=500 width=940)
default@src_orc_merge_test_part,src_orc_merge_test_part,Tbl:COMPLETE,Col:NONE
PREHOOK: query: explain select sum(hash(key)), sum(hash(value)) from src_orc_merge_test_part where ds='2012-01-03' and ts='2012-01-03+14:46:31'
@@ -1657,12 +1657,12 @@ Stage-0
<-Map 1 [PARTITION-LEVEL SORT]
PARTITION-LEVEL SORT [RS_6]
Select Operator [SEL_2] (rows=20 width=88)
- TableScan [TS_0] (rows=20 width=21)
+ TableScan [TS_0] (rows=20 width=139)
default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE
<-Map 4 [PARTITION-LEVEL SORT]
PARTITION-LEVEL SORT [RS_7]
Select Operator [SEL_5] (rows=20 width=88)
- TableScan [TS_3] (rows=20 width=21)
+ TableScan [TS_3] (rows=20 width=139)
default@cbo_t2,cbo_t2,Tbl:COMPLETE,Col:COMPLETE
PREHOOK: query: explain select *