You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by ha...@apache.org on 2017/12/12 00:00:19 UTC
[21/51] [partial] hive git commit: HIVE-13567 : Enable auto-gather
column stats by default (Zoltan Haindrich,
Pengcheng Xiong via Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/llap/dynpart_sort_opt_vectorization.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/dynpart_sort_opt_vectorization.q.out b/ql/src/test/results/clientpositive/llap/dynpart_sort_opt_vectorization.q.out
index ecc467a..15a97a7 100644
--- a/ql/src/test/results/clientpositive/llap/dynpart_sort_opt_vectorization.q.out
+++ b/ql/src/test/results/clientpositive/llap/dynpart_sort_opt_vectorization.q.out
@@ -173,19 +173,19 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: over1k_orc
- Statistics: Num rows: 1049 Data size: 23952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1049 Data size: 25160 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((t = 27) or t is null) (type: boolean)
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col4 (type: tinyint), _col0 (type: smallint)
sort order: ++
Map-reduce partition columns: _col4 (type: tinyint)
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: int), _col2 (type: bigint), _col3 (type: float)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -195,11 +195,11 @@ STAGE PLANS:
Select Operator
expressions: KEY._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), KEY._col4 (type: tinyint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
Dp Sort State: PARTITION_SORTED
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -225,6 +225,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: si, i, b, f
+ Column Types: smallint, int, bigint, float
+ Table: default.over1k_part_orc
PREHOOK: query: explain insert overwrite table over1k_part_limit_orc partition(ds="foo", t) select si,i,b,f,t from over1k_orc where t is null or t=27 limit 10
PREHOOK: type: QUERY
@@ -249,20 +253,20 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: over1k_orc
- Statistics: Num rows: 1049 Data size: 23952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1049 Data size: 25160 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((t = 27) or t is null) (type: boolean)
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
Limit
Number of rows: 10
- Statistics: Num rows: 10 Data size: 220 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 10 Data size: 220 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
Execution mode: vectorized, llap
@@ -273,15 +277,15 @@ STAGE PLANS:
Select Operator
expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), VALUE._col4 (type: tinyint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 10 Data size: 220 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE
Limit
Number of rows: 10
- Statistics: Num rows: 10 Data size: 220 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col4 (type: tinyint)
sort order: +
Map-reduce partition columns: _col4 (type: tinyint)
- Statistics: Num rows: 10 Data size: 220 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float)
Reducer 3
Execution mode: vectorized, llap
@@ -289,11 +293,11 @@ STAGE PLANS:
Select Operator
expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), KEY._col4 (type: tinyint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 10 Data size: 220 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
Dp Sort State: PARTITION_SORTED
- Statistics: Num rows: 10 Data size: 220 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -319,6 +323,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: si, i, b, f
+ Column Types: smallint, int, bigint, float
+ Table: default.over1k_part_limit_orc
PREHOOK: query: explain insert overwrite table over1k_part_buck_orc partition(t) select si,i,b,f,t from over1k_orc where t is null or t=27
PREHOOK: type: QUERY
@@ -342,19 +350,19 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: over1k_orc
- Statistics: Num rows: 1049 Data size: 23952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1049 Data size: 25160 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((t = 27) or t is null) (type: boolean)
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col4 (type: tinyint), '_bucket_number' (type: string)
sort order: ++
Map-reduce partition columns: _col4 (type: tinyint)
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -364,11 +372,11 @@ STAGE PLANS:
Select Operator
expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), KEY._col4 (type: tinyint), KEY.'_bucket_number' (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, '_bucket_number'
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1342 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
Dp Sort State: PARTITION_BUCKET_SORTED
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1342 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -393,6 +401,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: si, i, b, f
+ Column Types: smallint, int, bigint, float
+ Table: default.over1k_part_buck_orc
PREHOOK: query: explain insert overwrite table over1k_part_buck_sort_orc partition(t) select si,i,b,f,t from over1k_orc where t is null or t=27
PREHOOK: type: QUERY
@@ -416,19 +428,19 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: over1k_orc
- Statistics: Num rows: 1049 Data size: 23952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1049 Data size: 25160 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((t = 27) or t is null) (type: boolean)
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col4 (type: tinyint), '_bucket_number' (type: string), _col3 (type: float)
sort order: +++
Map-reduce partition columns: _col4 (type: tinyint)
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -438,11 +450,11 @@ STAGE PLANS:
Select Operator
expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), KEY._col3 (type: float), KEY._col4 (type: tinyint), KEY.'_bucket_number' (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, '_bucket_number'
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1342 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
Dp Sort State: PARTITION_BUCKET_SORTED
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1342 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -467,6 +479,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: si, i, b, f
+ Column Types: smallint, int, bigint, float
+ Table: default.over1k_part_buck_sort_orc
PREHOOK: query: insert overwrite table over1k_part_orc partition(ds="foo", t) select si,i,b,f,t from over1k_orc where t is null or t=27 order by si
PREHOOK: type: QUERY
@@ -558,19 +574,19 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: over1k_orc
- Statistics: Num rows: 1049 Data size: 23952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1049 Data size: 25160 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((t = 27) or t is null) (type: boolean)
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col4 (type: tinyint), _col0 (type: smallint)
sort order: ++
Map-reduce partition columns: _col4 (type: tinyint)
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: int), _col2 (type: bigint), _col3 (type: float)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -580,11 +596,11 @@ STAGE PLANS:
Select Operator
expressions: KEY._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), KEY._col4 (type: tinyint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
Dp Sort State: PARTITION_SORTED
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -610,6 +626,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: si, i, b, f
+ Column Types: smallint, int, bigint, float
+ Table: default.over1k_part_orc
PREHOOK: query: explain insert into table over1k_part_limit_orc partition(ds="foo", t) select si,i,b,f,t from over1k_orc where t is null or t=27 limit 10
PREHOOK: type: QUERY
@@ -634,20 +654,20 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: over1k_orc
- Statistics: Num rows: 1049 Data size: 23952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1049 Data size: 25160 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((t = 27) or t is null) (type: boolean)
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
Limit
Number of rows: 10
- Statistics: Num rows: 10 Data size: 220 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 10 Data size: 220 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
Execution mode: vectorized, llap
@@ -658,15 +678,15 @@ STAGE PLANS:
Select Operator
expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), VALUE._col4 (type: tinyint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 10 Data size: 220 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE
Limit
Number of rows: 10
- Statistics: Num rows: 10 Data size: 220 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col4 (type: tinyint)
sort order: +
Map-reduce partition columns: _col4 (type: tinyint)
- Statistics: Num rows: 10 Data size: 220 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float)
Reducer 3
Execution mode: vectorized, llap
@@ -674,11 +694,11 @@ STAGE PLANS:
Select Operator
expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), KEY._col4 (type: tinyint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 10 Data size: 220 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
Dp Sort State: PARTITION_SORTED
- Statistics: Num rows: 10 Data size: 220 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -704,6 +724,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: si, i, b, f
+ Column Types: smallint, int, bigint, float
+ Table: default.over1k_part_limit_orc
PREHOOK: query: explain insert into table over1k_part_buck_orc partition(t) select si,i,b,f,t from over1k_orc where t is null or t=27
PREHOOK: type: QUERY
@@ -727,19 +751,19 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: over1k_orc
- Statistics: Num rows: 1049 Data size: 23952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1049 Data size: 25160 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((t = 27) or t is null) (type: boolean)
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col4 (type: tinyint), '_bucket_number' (type: string)
sort order: ++
Map-reduce partition columns: _col4 (type: tinyint)
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -749,11 +773,11 @@ STAGE PLANS:
Select Operator
expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), KEY._col4 (type: tinyint), KEY.'_bucket_number' (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, '_bucket_number'
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1342 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
Dp Sort State: PARTITION_BUCKET_SORTED
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1342 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -778,6 +802,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: si, i, b, f
+ Column Types: smallint, int, bigint, float
+ Table: default.over1k_part_buck_orc
PREHOOK: query: explain insert into table over1k_part_buck_sort_orc partition(t) select si,i,b,f,t from over1k_orc where t is null or t=27
PREHOOK: type: QUERY
@@ -801,19 +829,19 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: over1k_orc
- Statistics: Num rows: 1049 Data size: 23952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1049 Data size: 25160 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((t = 27) or t is null) (type: boolean)
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col4 (type: tinyint), '_bucket_number' (type: string), _col3 (type: float)
sort order: +++
Map-reduce partition columns: _col4 (type: tinyint)
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -823,11 +851,11 @@ STAGE PLANS:
Select Operator
expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), KEY._col3 (type: float), KEY._col4 (type: tinyint), KEY.'_bucket_number' (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, '_bucket_number'
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1342 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
Dp Sort State: PARTITION_BUCKET_SORTED
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1342 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -852,6 +880,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: si, i, b, f
+ Column Types: smallint, int, bigint, float
+ Table: default.over1k_part_buck_sort_orc
PREHOOK: query: insert into table over1k_part_orc partition(ds="foo", t) select si,i,b,f,t from over1k_orc where t is null or t=27 order by si
PREHOOK: type: QUERY
@@ -944,7 +976,7 @@ Database: default
Table: over1k_part_orc
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"f\":\"true\",\"i\":\"true\",\"si\":\"true\"}}
numFiles 2
numRows 32
rawDataSize 640
@@ -984,7 +1016,7 @@ Database: default
Table: over1k_part_orc
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"f\":\"true\",\"i\":\"true\",\"si\":\"true\"}}
numFiles 2
numRows 6
rawDataSize 120
@@ -1024,7 +1056,7 @@ Database: default
Table: over1k_part_limit_orc
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"f\":\"true\",\"i\":\"true\",\"si\":\"true\"}}
numFiles 2
numRows 14
rawDataSize 280
@@ -1064,7 +1096,7 @@ Database: default
Table: over1k_part_limit_orc
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"f\":\"true\",\"i\":\"true\",\"si\":\"true\"}}
numFiles 2
numRows 6
rawDataSize 120
@@ -1103,7 +1135,7 @@ Database: default
Table: over1k_part_buck_orc
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"f\":\"true\",\"i\":\"true\",\"si\":\"true\"}}
numFiles 2
numRows 32
rawDataSize 640
@@ -1142,7 +1174,7 @@ Database: default
Table: over1k_part_buck_orc
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"f\":\"true\",\"i\":\"true\",\"si\":\"true\"}}
numFiles 2
numRows 4
rawDataSize 80
@@ -1181,7 +1213,7 @@ Database: default
Table: over1k_part_buck_sort_orc
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"f\":\"true\",\"i\":\"true\",\"si\":\"true\"}}
numFiles 2
numRows 32
rawDataSize 640
@@ -1220,7 +1252,7 @@ Database: default
Table: over1k_part_buck_sort_orc
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"f\":\"true\",\"i\":\"true\",\"si\":\"true\"}}
numFiles 2
numRows 4
rawDataSize 80
@@ -1323,42 +1355,79 @@ STAGE PLANS:
#### A masked pattern was here ####
Edges:
Reducer 2 <- Map 1 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
alias: over1k_orc
- Statistics: Num rows: 1049 Data size: 23952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1049 Data size: 25160 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((t = 27) or t is null) (type: boolean)
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: int)
sort order: +
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: smallint), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
Execution mode: vectorized, llap
LLAP IO: all inputs
Reducer 2
- Execution mode: vectorized, llap
+ Execution mode: llap
Reduce Operator Tree:
Select Operator
expressions: VALUE._col0 (type: smallint), KEY.reducesinkkey0 (type: int), VALUE._col1 (type: bigint), VALUE._col2 (type: float), VALUE._col3 (type: tinyint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.over1k_part2_orc
+ Select Operator
+ expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), 'foo' (type: string), _col4 (type: tinyint)
+ outputColumnNames: si, i, b, f, ds, t
+ Statistics: Num rows: 11 Data size: 1221 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(si, 'hll'), compute_stats(i, 'hll'), compute_stats(b, 'hll'), compute_stats(f, 'hll')
+ keys: ds (type: string), t (type: tinyint)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 2 Data size: 3574 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: tinyint)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: tinyint)
+ Statistics: Num rows: 2 Data size: 3574 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col4 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col5 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:binary>)
+ Reducer 3
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3)
+ keys: KEY._col0 (type: string), KEY._col1 (type: tinyint)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 2 Data size: 3702 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col4 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col5 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: tinyint)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 2 Data size: 3702 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 2 Data size: 3702 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-2
Dependency Collection
@@ -1379,6 +1448,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: si, i, b, f
+ Column Types: smallint, int, bigint, float
+ Table: default.over1k_part2_orc
PREHOOK: query: explain insert overwrite table over1k_part2_orc partition(ds="foo",t) select si,i,b,f,t from over1k_orc where t is null or t=27 order by i
PREHOOK: type: QUERY
@@ -1402,19 +1475,19 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: over1k_orc
- Statistics: Num rows: 1049 Data size: 23952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1049 Data size: 25160 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((t = 27) or t is null) (type: boolean)
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col4 (type: tinyint), _col1 (type: int)
sort order: ++
Map-reduce partition columns: _col4 (type: tinyint)
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: smallint), _col2 (type: bigint), _col3 (type: float)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1424,11 +1497,11 @@ STAGE PLANS:
Select Operator
expressions: VALUE._col0 (type: smallint), KEY._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), KEY._col4 (type: tinyint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
Dp Sort State: PARTITION_SORTED
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -1454,6 +1527,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: si, i, b, f
+ Column Types: smallint, int, bigint, float
+ Table: default.over1k_part2_orc
PREHOOK: query: explain insert overwrite table over1k_part2_orc partition(ds="foo",t) select si,i,b,f,t from (select * from over1k_orc order by i limit 10) tmp where t is null or t=27
PREHOOK: type: QUERY
@@ -1478,15 +1555,15 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: over1k_orc
- Statistics: Num rows: 1049 Data size: 23952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1049 Data size: 25160 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: t (type: tinyint), si (type: smallint), i (type: int), b (type: bigint), f (type: float)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 1049 Data size: 23952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1049 Data size: 25160 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col2 (type: int)
sort order: +
- Statistics: Num rows: 1049 Data size: 23952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1049 Data size: 25160 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col3 (type: bigint), _col4 (type: float)
Execution mode: vectorized, llap
@@ -1497,22 +1574,22 @@ STAGE PLANS:
Select Operator
expressions: VALUE._col0 (type: tinyint), VALUE._col1 (type: smallint), KEY.reducesinkkey0 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 1049 Data size: 23952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1049 Data size: 25160 Basic stats: COMPLETE Column stats: COMPLETE
Limit
Number of rows: 10
- Statistics: Num rows: 10 Data size: 220 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((_col0 = 27) or _col0 is null) (type: boolean)
- Statistics: Num rows: 10 Data size: 220 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col0 (type: tinyint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 10 Data size: 220 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col4 (type: tinyint)
sort order: +
Map-reduce partition columns: _col4 (type: tinyint)
- Statistics: Num rows: 10 Data size: 220 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float)
Reducer 3
Execution mode: vectorized, llap
@@ -1520,11 +1597,11 @@ STAGE PLANS:
Select Operator
expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), KEY._col4 (type: tinyint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 10 Data size: 220 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
Dp Sort State: PARTITION_SORTED
- Statistics: Num rows: 10 Data size: 220 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -1550,6 +1627,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: si, i, b, f
+ Column Types: smallint, int, bigint, float
+ Table: default.over1k_part2_orc
PREHOOK: query: explain insert overwrite table over1k_part2_orc partition(ds="foo",t) select si,i,b,f,t from over1k_orc where t is null or t=27 group by si,i,b,f,t
PREHOOK: type: QUERY
@@ -1567,48 +1648,85 @@ STAGE PLANS:
#### A masked pattern was here ####
Edges:
Reducer 2 <- Map 1 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
alias: over1k_orc
- Statistics: Num rows: 1049 Data size: 23952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1049 Data size: 25160 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((t = 27) or t is null) (type: boolean)
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: t (type: tinyint), si (type: smallint), i (type: int), b (type: bigint), f (type: float)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float)
sort order: +++++
Map-reduce partition columns: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float)
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Reducer 2
- Execution mode: vectorized, llap
+ Execution mode: llap
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: tinyint), KEY._col1 (type: smallint), KEY._col2 (type: int), KEY._col3 (type: bigint), KEY._col4 (type: float)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 28 Data size: 639 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col0 (type: tinyint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 28 Data size: 639 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 28 Data size: 639 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.over1k_part2_orc
+ Select Operator
+ expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), 'foo' (type: string), _col4 (type: tinyint)
+ outputColumnNames: si, i, b, f, ds, t
+ Statistics: Num rows: 5 Data size: 555 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(si, 'hll'), compute_stats(i, 'hll'), compute_stats(b, 'hll'), compute_stats(f, 'hll')
+ keys: ds (type: string), t (type: tinyint)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 2 Data size: 3574 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: tinyint)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: tinyint)
+ Statistics: Num rows: 2 Data size: 3574 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col4 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col5 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:binary>)
+ Reducer 3
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3)
+ keys: KEY._col0 (type: string), KEY._col1 (type: tinyint)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 2 Data size: 3702 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col4 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col5 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: tinyint)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 2 Data size: 3702 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 2 Data size: 3702 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-2
Dependency Collection
@@ -1629,6 +1747,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: si, i, b, f
+ Column Types: smallint, int, bigint, float
+ Table: default.over1k_part2_orc
PREHOOK: query: explain insert overwrite table over1k_part2_orc partition(ds="foo",t) select si,i,b,f,t from over1k_orc where t is null or t=27 group by si,i,b,f,t
PREHOOK: type: QUERY
@@ -1652,20 +1774,20 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: over1k_orc
- Statistics: Num rows: 1049 Data size: 23952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1049 Data size: 25160 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((t = 27) or t is null) (type: boolean)
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: t (type: tinyint), si (type: smallint), i (type: int), b (type: bigint), f (type: float)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float)
sort order: +++++
Map-reduce partition columns: _col0 (type: tinyint)
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Reducer 2
@@ -1675,15 +1797,15 @@ STAGE PLANS:
keys: KEY._col0 (type: tinyint), KEY._col1 (type: smallint), KEY._col2 (type: int), KEY._col3 (type: bigint), KEY._col4 (type: float)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 28 Data size: 639 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col0 (type: tinyint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 28 Data size: 639 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
Dp Sort State: PARTITION_SORTED
- Statistics: Num rows: 28 Data size: 639 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -1709,6 +1831,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: si, i, b, f
+ Column Types: smallint, int, bigint, float
+ Table: default.over1k_part2_orc
PREHOOK: query: insert overwrite table over1k_part2_orc partition(ds="foo",t) select si,i,b,f,t from over1k_orc where t is null or t=27 order by i
PREHOOK: type: QUERY
@@ -1750,7 +1876,7 @@ Database: default
Table: over1k_part2_orc
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"f\":\"true\",\"i\":\"true\",\"si\":\"true\"}}
numFiles 1
numRows 16
rawDataSize 415
@@ -1790,7 +1916,7 @@ Database: default
Table: over1k_part2_orc
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"f\":\"true\",\"i\":\"true\",\"si\":\"true\"}}
numFiles 1
numRows 3
rawDataSize 78
@@ -1891,7 +2017,7 @@ Database: default
Table: over1k_part2_orc
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"f\":\"true\",\"i\":\"true\",\"si\":\"true\"}}
numFiles 1
numRows 16
rawDataSize 415
@@ -1931,7 +2057,7 @@ Database: default
Table: over1k_part2_orc
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"f\":\"true\",\"i\":\"true\",\"si\":\"true\"}}
numFiles 1
numRows 3
rawDataSize 78
@@ -2030,43 +2156,80 @@ STAGE PLANS:
#### A masked pattern was here ####
Edges:
Reducer 2 <- Map 1 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
alias: over1k_orc
- Statistics: Num rows: 1049 Data size: 23952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1049 Data size: 25160 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((t = 27) or t is null) (type: boolean)
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col3 (type: float)
sort order: +
Map-reduce partition columns: _col0 (type: smallint)
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col4 (type: tinyint)
Execution mode: vectorized, llap
LLAP IO: all inputs
Reducer 2
- Execution mode: vectorized, llap
+ Execution mode: llap
Reduce Operator Tree:
Select Operator
expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), KEY.reducesinkkey0 (type: float), VALUE._col3 (type: tinyint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.over1k_part_buck_sort2_orc
+ Select Operator
+ expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+ outputColumnNames: si, i, b, f, t
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(si, 'hll'), compute_stats(i, 'hll'), compute_stats(b, 'hll'), compute_stats(f, 'hll')
+ keys: t (type: tinyint)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 2 Data size: 3400 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: tinyint)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: tinyint)
+ Statistics: Num rows: 2 Data size: 3400 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col4 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:binary>)
+ Reducer 3
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3)
+ keys: KEY._col0 (type: tinyint)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 2 Data size: 3528 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col4 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: tinyint)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 2 Data size: 3528 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 2 Data size: 3528 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-2
Dependency Collection
@@ -2086,6 +2249,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: si, i, b, f
+ Column Types: smallint, int, bigint, float
+ Table: default.over1k_part_buck_sort2_orc
PREHOOK: query: explain insert overwrite table over1k_part_buck_sort2_orc partition(t) select si,i,b,f,t from over1k_orc where t is null or t=27
PREHOOK: type: QUERY
@@ -2109,19 +2276,19 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: over1k_orc
- Statistics: Num rows: 1049 Data size: 23952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1049 Data size: 25160 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((t = 27) or t is null) (type: boolean)
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col4 (type: tinyint), '_bucket_number' (type: string), _col3 (type: float)
sort order: +++
Map-reduce partition columns: _col4 (type: tinyint)
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -2131,11 +2298,11 @@ STAGE PLANS:
Select Operator
expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), KEY._col3 (type: float), KEY._col4 (type: tinyint), KEY.'_bucket_number' (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, '_bucket_number'
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1342 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
Dp Sort State: PARTITION_BUCKET_SORTED
- Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1342 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -2160,6 +2327,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: si, i, b, f
+ Column Types: smallint, int, bigint, float
+ Table: default.over1k_part_buck_sort2_orc
PREHOOK: query: insert overwrite table over1k_part_buck_sort2_orc partition(t) select si,i,b,f,t from over1k_orc where t is null or t=27
PREHOOK: type: QUERY
@@ -2200,7 +2371,7 @@ Database: default
Table: over1k_part_buck_sort2_orc
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"f\":\"true\",\"i\":\"true\",\"si\":\"true\"}}
numFiles 1
numRows 16
rawDataSize 415
@@ -2239,7 +2410,7 @@ Database: default
Table: over1k_part_buck_sort2_orc
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"f\":\"true\",\"i\":\"true\",\"si\":\"true\"}}
numFiles 1
numRows 3
rawDataSize 78
@@ -2414,7 +2585,7 @@ Database: default
Table: over1k_part_buck_sort2_orc
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"f\":\"true\",\"i\":\"true\",\"si\":\"true\"}}
numFiles 1
numRows 16
rawDataSize 415
@@ -2453,7 +2624,7 @@ Database: default
Table: over1k_part_buck_sort2_orc
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"f\":\"true\",\"i\":\"true\",\"si\":\"true\"}}
numFiles 1
numRows 2
rawDataSize 52