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 2018/06/28 09:45:20 UTC
[4/9] hive git commit: HIVE-18140: Partitioned tables statistics can
go wrong in basic stats mixed case (Zoltan Haindrich reviewed by Ashutosh
Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/15d7d6dc/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization_acid.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization_acid.q.out b/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization_acid.q.out
index 7a9e200..33bceed 100644
--- a/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization_acid.q.out
+++ b/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization_acid.q.out
@@ -95,19 +95,19 @@ STAGE PLANS:
TableScan
alias: acid_part
filterExpr: ((key = 'foo') and (ds = '2008-04-08')) (type: boolean)
- Statistics: Num rows: 160 Data size: 61001 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 160 Data size: 61001 Basic stats: PARTIAL Column stats: NONE
Filter Operator
predicate: (key = 'foo') (type: boolean)
- Statistics: Num rows: 5 Data size: 1906 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1906 Basic stats: PARTIAL Column stats: NONE
Select Operator
expressions: ROW__ID (type: struct<writeid:bigint,bucketid:int,rowid:bigint>)
outputColumnNames: _col0
- Statistics: Num rows: 5 Data size: 1906 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1906 Basic stats: PARTIAL Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>)
sort order: +
Map-reduce partition columns: UDFToInteger(_col0) (type: int)
- Statistics: Num rows: 5 Data size: 1906 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1906 Basic stats: PARTIAL Column stats: NONE
Execution mode: llap
LLAP IO: may be used (ACID table)
Reducer 2
@@ -116,10 +116,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>), 'foo' (type: string), 'bar' (type: string), '2008-04-08' (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 5 Data size: 1906 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1906 Basic stats: PARTIAL Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 5 Data size: 1906 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1906 Basic stats: PARTIAL Column stats: NONE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -191,19 +191,19 @@ STAGE PLANS:
TableScan
alias: acid_part
filterExpr: ((key = 'foo') and (ds) IN ('2008-04-08')) (type: boolean)
- Statistics: Num rows: 159 Data size: 104317 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 159 Data size: 104317 Basic stats: PARTIAL Column stats: PARTIAL
Filter Operator
predicate: (key = 'foo') (type: boolean)
- Statistics: Num rows: 5 Data size: 1355 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 3280 Basic stats: PARTIAL Column stats: PARTIAL
Select Operator
expressions: ROW__ID (type: struct<writeid:bigint,bucketid:int,rowid:bigint>), ds (type: string)
outputColumnNames: _col0, _col3
- Statistics: Num rows: 5 Data size: 2170 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 3280 Basic stats: PARTIAL Column stats: PARTIAL
Reduce Output Operator
key expressions: _col0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>)
sort order: +
Map-reduce partition columns: UDFToInteger(_col0) (type: int)
- Statistics: Num rows: 5 Data size: 2170 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 3280 Basic stats: PARTIAL Column stats: PARTIAL
value expressions: _col3 (type: string)
Execution mode: llap
LLAP IO: may be used (ACID table)
@@ -213,10 +213,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>), 'foo' (type: string), 'bar' (type: string), VALUE._col1 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 5 Data size: 2170 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 3280 Basic stats: PARTIAL Column stats: PARTIAL
File Output Operator
compressed: false
- Statistics: Num rows: 5 Data size: 2170 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 3280 Basic stats: PARTIAL Column stats: PARTIAL
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -383,19 +383,19 @@ STAGE PLANS:
TableScan
alias: acid_part_sdpo
filterExpr: ((key = 'foo') and (ds = '2008-04-08')) (type: boolean)
- Statistics: Num rows: 176 Data size: 67063 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 176 Data size: 67063 Basic stats: PARTIAL Column stats: NONE
Filter Operator
predicate: (key = 'foo') (type: boolean)
- Statistics: Num rows: 5 Data size: 1905 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1905 Basic stats: PARTIAL Column stats: NONE
Select Operator
expressions: ROW__ID (type: struct<writeid:bigint,bucketid:int,rowid:bigint>)
outputColumnNames: _col0
- Statistics: Num rows: 5 Data size: 1905 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1905 Basic stats: PARTIAL Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>)
sort order: +
Map-reduce partition columns: UDFToInteger(_col0) (type: int)
- Statistics: Num rows: 5 Data size: 1905 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1905 Basic stats: PARTIAL Column stats: NONE
Execution mode: llap
LLAP IO: may be used (ACID table)
Reducer 2
@@ -404,10 +404,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>), 'foo' (type: string), 'bar' (type: string), '2008-04-08' (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 5 Data size: 1905 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1905 Basic stats: PARTIAL Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 5 Data size: 1905 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1905 Basic stats: PARTIAL Column stats: NONE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -479,19 +479,19 @@ STAGE PLANS:
TableScan
alias: acid_part_sdpo
filterExpr: ((key = 'foo') and (ds) IN ('2008-04-08')) (type: boolean)
- Statistics: Num rows: 171 Data size: 112152 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 171 Data size: 112152 Basic stats: PARTIAL Column stats: PARTIAL
Filter Operator
predicate: (key = 'foo') (type: boolean)
- Statistics: Num rows: 5 Data size: 1355 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 3279 Basic stats: PARTIAL Column stats: PARTIAL
Select Operator
expressions: ROW__ID (type: struct<writeid:bigint,bucketid:int,rowid:bigint>), ds (type: string)
outputColumnNames: _col0, _col3
- Statistics: Num rows: 5 Data size: 2170 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 3279 Basic stats: PARTIAL Column stats: PARTIAL
Reduce Output Operator
key expressions: _col3 (type: string), '_bucket_number' (type: string), _col0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>)
sort order: +++
Map-reduce partition columns: _col3 (type: string)
- Statistics: Num rows: 5 Data size: 2170 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 3279 Basic stats: PARTIAL Column stats: PARTIAL
Execution mode: llap
LLAP IO: may be used (ACID table)
Reducer 2
@@ -500,11 +500,11 @@ STAGE PLANS:
Select Operator
expressions: KEY._col0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>), 'foo' (type: string), 'bar' (type: string), KEY._col3 (type: string), KEY.'_bucket_number' (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, '_bucket_number'
- Statistics: Num rows: 5 Data size: 1790 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 3279 Basic stats: PARTIAL Column stats: PARTIAL
File Output Operator
compressed: false
Dp Sort State: PARTITION_BUCKET_SORTED
- Statistics: Num rows: 5 Data size: 1790 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 3279 Basic stats: PARTIAL Column stats: PARTIAL
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -680,19 +680,19 @@ STAGE PLANS:
TableScan
alias: acid_2l_part
filterExpr: ((key = 'foo') and (ds = '2008-04-08') and (hr = 11)) (type: boolean)
- Statistics: Num rows: 157 Data size: 60527 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 157 Data size: 60527 Basic stats: PARTIAL Column stats: NONE
Filter Operator
predicate: (key = 'foo') (type: boolean)
- Statistics: Num rows: 5 Data size: 1927 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1927 Basic stats: PARTIAL Column stats: NONE
Select Operator
expressions: ROW__ID (type: struct<writeid:bigint,bucketid:int,rowid:bigint>)
outputColumnNames: _col0
- Statistics: Num rows: 5 Data size: 1927 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1927 Basic stats: PARTIAL Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>)
sort order: +
Map-reduce partition columns: UDFToInteger(_col0) (type: int)
- Statistics: Num rows: 5 Data size: 1927 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1927 Basic stats: PARTIAL Column stats: NONE
Execution mode: llap
LLAP IO: may be used (ACID table)
Reducer 2
@@ -701,10 +701,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>), 'foo' (type: string), 'bar' (type: string), '2008-04-08' (type: string), 11 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 5 Data size: 1927 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1927 Basic stats: PARTIAL Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 5 Data size: 1927 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1927 Basic stats: PARTIAL Column stats: NONE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -777,19 +777,19 @@ STAGE PLANS:
TableScan
alias: acid_2l_part
filterExpr: ((key = 'foo') and (ds = '2008-04-08') and (hr >= 11)) (type: boolean)
- Statistics: Num rows: 1600 Data size: 156727 Basic stats: PARTIAL Column stats: PARTIAL
+ Statistics: Num rows: 1804 Data size: 235871 Basic stats: PARTIAL Column stats: PARTIAL
Filter Operator
predicate: (key = 'foo') (type: boolean)
- Statistics: Num rows: 5 Data size: 489 Basic stats: PARTIAL Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 653 Basic stats: PARTIAL Column stats: PARTIAL
Select Operator
expressions: ROW__ID (type: struct<writeid:bigint,bucketid:int,rowid:bigint>), hr (type: int)
outputColumnNames: _col0, _col4
- Statistics: Num rows: 5 Data size: 489 Basic stats: PARTIAL Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 653 Basic stats: PARTIAL Column stats: PARTIAL
Reduce Output Operator
key expressions: _col0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>)
sort order: +
Map-reduce partition columns: UDFToInteger(_col0) (type: int)
- Statistics: Num rows: 5 Data size: 489 Basic stats: PARTIAL Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 653 Basic stats: PARTIAL Column stats: PARTIAL
value expressions: _col4 (type: int)
Execution mode: llap
LLAP IO: may be used (ACID table)
@@ -799,10 +799,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>), 'foo' (type: string), 'bar' (type: string), '2008-04-08' (type: string), VALUE._col2 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 5 Data size: 489 Basic stats: PARTIAL Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 653 Basic stats: PARTIAL Column stats: PARTIAL
File Output Operator
compressed: false
- Statistics: Num rows: 5 Data size: 489 Basic stats: PARTIAL Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 653 Basic stats: PARTIAL Column stats: PARTIAL
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -904,19 +904,19 @@ STAGE PLANS:
TableScan
alias: acid_2l_part
filterExpr: (value = 'bar') (type: boolean)
- Statistics: Num rows: 1600 Data size: 451127 Basic stats: PARTIAL Column stats: PARTIAL
+ Statistics: Num rows: 2015 Data size: 726272 Basic stats: PARTIAL Column stats: PARTIAL
Filter Operator
predicate: (value = 'bar') (type: boolean)
- Statistics: Num rows: 5 Data size: 1409 Basic stats: PARTIAL Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 1802 Basic stats: PARTIAL Column stats: PARTIAL
Select Operator
expressions: ROW__ID (type: struct<writeid:bigint,bucketid:int,rowid:bigint>), ds (type: string), hr (type: int)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 5 Data size: 1409 Basic stats: PARTIAL Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 1802 Basic stats: PARTIAL Column stats: PARTIAL
Reduce Output Operator
key expressions: _col0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>)
sort order: +
Map-reduce partition columns: UDFToInteger(_col0) (type: int)
- Statistics: Num rows: 5 Data size: 1409 Basic stats: PARTIAL Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 1802 Basic stats: PARTIAL Column stats: PARTIAL
value expressions: _col1 (type: string), _col2 (type: int)
Execution mode: llap
LLAP IO: may be used (ACID table)
@@ -926,10 +926,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>), VALUE._col0 (type: string), VALUE._col1 (type: int)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 5 Data size: 1409 Basic stats: PARTIAL Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 1802 Basic stats: PARTIAL Column stats: PARTIAL
File Output Operator
compressed: false
- Statistics: Num rows: 5 Data size: 1409 Basic stats: PARTIAL Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 1802 Basic stats: PARTIAL Column stats: PARTIAL
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -1103,19 +1103,19 @@ STAGE PLANS:
TableScan
alias: acid_2l_part_sdpo
filterExpr: ((key = 'foo') and (ds = '2008-04-08') and (hr = 11)) (type: boolean)
- Statistics: Num rows: 157 Data size: 60527 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 157 Data size: 60527 Basic stats: PARTIAL Column stats: NONE
Filter Operator
predicate: (key = 'foo') (type: boolean)
- Statistics: Num rows: 5 Data size: 1927 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1927 Basic stats: PARTIAL Column stats: NONE
Select Operator
expressions: ROW__ID (type: struct<writeid:bigint,bucketid:int,rowid:bigint>)
outputColumnNames: _col0
- Statistics: Num rows: 5 Data size: 1927 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1927 Basic stats: PARTIAL Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>)
sort order: +
Map-reduce partition columns: UDFToInteger(_col0) (type: int)
- Statistics: Num rows: 5 Data size: 1927 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1927 Basic stats: PARTIAL Column stats: NONE
Execution mode: llap
LLAP IO: may be used (ACID table)
Reducer 2
@@ -1124,10 +1124,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>), 'foo' (type: string), 'bar' (type: string), '2008-04-08' (type: string), 11 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 5 Data size: 1927 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1927 Basic stats: PARTIAL Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 5 Data size: 1927 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1927 Basic stats: PARTIAL Column stats: NONE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -1200,19 +1200,19 @@ STAGE PLANS:
TableScan
alias: acid_2l_part_sdpo
filterExpr: ((key = 'foo') and (ds = '2008-04-08') and (hr >= 11)) (type: boolean)
- Statistics: Num rows: 1600 Data size: 156727 Basic stats: PARTIAL Column stats: PARTIAL
+ Statistics: Num rows: 1804 Data size: 235871 Basic stats: PARTIAL Column stats: PARTIAL
Filter Operator
predicate: (key = 'foo') (type: boolean)
- Statistics: Num rows: 5 Data size: 489 Basic stats: PARTIAL Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 653 Basic stats: PARTIAL Column stats: PARTIAL
Select Operator
expressions: ROW__ID (type: struct<writeid:bigint,bucketid:int,rowid:bigint>), hr (type: int)
outputColumnNames: _col0, _col4
- Statistics: Num rows: 5 Data size: 489 Basic stats: PARTIAL Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 653 Basic stats: PARTIAL Column stats: PARTIAL
Reduce Output Operator
key expressions: '2008-04-08' (type: string), _col4 (type: int), '_bucket_number' (type: string), _col0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>)
sort order: ++++
Map-reduce partition columns: '2008-04-08' (type: string), _col4 (type: int)
- Statistics: Num rows: 5 Data size: 489 Basic stats: PARTIAL Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 653 Basic stats: PARTIAL Column stats: PARTIAL
Execution mode: llap
LLAP IO: may be used (ACID table)
Reducer 2
@@ -1221,11 +1221,11 @@ STAGE PLANS:
Select Operator
expressions: KEY._col0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>), 'foo' (type: string), 'bar' (type: string), '2008-04-08' (type: string), KEY._col4 (type: int), KEY.'_bucket_number' (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, '_bucket_number'
- Statistics: Num rows: 5 Data size: 489 Basic stats: PARTIAL Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 653 Basic stats: PARTIAL Column stats: PARTIAL
File Output Operator
compressed: false
Dp Sort State: PARTITION_BUCKET_SORTED
- Statistics: Num rows: 5 Data size: 489 Basic stats: PARTIAL Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 653 Basic stats: PARTIAL Column stats: PARTIAL
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -1327,19 +1327,19 @@ STAGE PLANS:
TableScan
alias: acid_2l_part_sdpo
filterExpr: (value = 'bar') (type: boolean)
- Statistics: Num rows: 1600 Data size: 451127 Basic stats: PARTIAL Column stats: PARTIAL
+ Statistics: Num rows: 2015 Data size: 726272 Basic stats: PARTIAL Column stats: PARTIAL
Filter Operator
predicate: (value = 'bar') (type: boolean)
- Statistics: Num rows: 5 Data size: 1409 Basic stats: PARTIAL Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 1802 Basic stats: PARTIAL Column stats: PARTIAL
Select Operator
expressions: ROW__ID (type: struct<writeid:bigint,bucketid:int,rowid:bigint>), ds (type: string), hr (type: int)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 5 Data size: 1409 Basic stats: PARTIAL Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 1802 Basic stats: PARTIAL Column stats: PARTIAL
Reduce Output Operator
key expressions: _col1 (type: string), _col2 (type: int), '_bucket_number' (type: string), _col0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>)
sort order: ++++
Map-reduce partition columns: _col1 (type: string), _col2 (type: int)
- Statistics: Num rows: 5 Data size: 1409 Basic stats: PARTIAL Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 1802 Basic stats: PARTIAL Column stats: PARTIAL
Execution mode: llap
LLAP IO: may be used (ACID table)
Reducer 2
@@ -1348,11 +1348,11 @@ STAGE PLANS:
Select Operator
expressions: KEY._col0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>), KEY._col1 (type: string), KEY._col2 (type: int), KEY.'_bucket_number' (type: string)
outputColumnNames: _col0, _col1, _col2, '_bucket_number'
- Statistics: Num rows: 5 Data size: 1409 Basic stats: PARTIAL Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 1802 Basic stats: PARTIAL Column stats: PARTIAL
File Output Operator
compressed: false
Dp Sort State: PARTITION_BUCKET_SORTED
- Statistics: Num rows: 5 Data size: 1409 Basic stats: PARTIAL Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 1802 Basic stats: PARTIAL Column stats: PARTIAL
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -1526,19 +1526,19 @@ STAGE PLANS:
TableScan
alias: acid_2l_part_sdpo_no_cp
filterExpr: ((key = 'foo') and (ds = '2008-04-08') and (hr = 11)) (type: boolean)
- Statistics: Num rows: 97 Data size: 82922 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 97 Data size: 82922 Basic stats: PARTIAL Column stats: PARTIAL
Filter Operator
predicate: (key = 'foo') (type: boolean)
- Statistics: Num rows: 5 Data size: 1860 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 4274 Basic stats: PARTIAL Column stats: PARTIAL
Select Operator
expressions: ROW__ID (type: struct<writeid:bigint,bucketid:int,rowid:bigint>), key (type: string), ds (type: string), hr (type: int)
outputColumnNames: _col0, _col1, _col3, _col4
- Statistics: Num rows: 5 Data size: 2675 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 4274 Basic stats: PARTIAL Column stats: PARTIAL
Reduce Output Operator
key expressions: _col3 (type: string), _col4 (type: int), '_bucket_number' (type: string), _col0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>)
sort order: ++++
Map-reduce partition columns: _col3 (type: string), _col4 (type: int)
- Statistics: Num rows: 5 Data size: 2675 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 4274 Basic stats: PARTIAL Column stats: PARTIAL
value expressions: _col1 (type: string), 'bar' (type: string)
Execution mode: llap
LLAP IO: may be used (ACID table)
@@ -1548,11 +1548,11 @@ STAGE PLANS:
Select Operator
expressions: KEY._col0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: int), KEY.'_bucket_number' (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, '_bucket_number'
- Statistics: Num rows: 5 Data size: 3165 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 4274 Basic stats: PARTIAL Column stats: PARTIAL
File Output Operator
compressed: false
Dp Sort State: PARTITION_BUCKET_SORTED
- Statistics: Num rows: 5 Data size: 3165 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 4274 Basic stats: PARTIAL Column stats: PARTIAL
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -1625,19 +1625,19 @@ STAGE PLANS:
TableScan
alias: acid_2l_part_sdpo_no_cp
filterExpr: ((key = 'foo') and (ds = '2008-04-08') and (hr >= 11)) (type: boolean)
- Statistics: Num rows: 1600 Data size: 598664 Basic stats: PARTIAL Column stats: PARTIAL
+ Statistics: Num rows: 1725 Data size: 705510 Basic stats: PARTIAL Column stats: PARTIAL
Filter Operator
predicate: (key = 'foo') (type: boolean)
- Statistics: Num rows: 5 Data size: 1870 Basic stats: PARTIAL Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 2044 Basic stats: PARTIAL Column stats: PARTIAL
Select Operator
expressions: ROW__ID (type: struct<writeid:bigint,bucketid:int,rowid:bigint>), key (type: string), ds (type: string), hr (type: int)
outputColumnNames: _col0, _col1, _col3, _col4
- Statistics: Num rows: 5 Data size: 1870 Basic stats: PARTIAL Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 2044 Basic stats: PARTIAL Column stats: PARTIAL
Reduce Output Operator
key expressions: _col3 (type: string), _col4 (type: int), '_bucket_number' (type: string), _col0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>)
sort order: ++++
Map-reduce partition columns: _col3 (type: string), _col4 (type: int)
- Statistics: Num rows: 5 Data size: 1870 Basic stats: PARTIAL Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 2044 Basic stats: PARTIAL Column stats: PARTIAL
value expressions: _col1 (type: string), 'bar' (type: string)
Execution mode: llap
LLAP IO: may be used (ACID table)
@@ -1647,11 +1647,11 @@ STAGE PLANS:
Select Operator
expressions: KEY._col0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: int), KEY.'_bucket_number' (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, '_bucket_number'
- Statistics: Num rows: 5 Data size: 1870 Basic stats: PARTIAL Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 2044 Basic stats: PARTIAL Column stats: PARTIAL
File Output Operator
compressed: false
Dp Sort State: PARTITION_BUCKET_SORTED
- Statistics: Num rows: 5 Data size: 1870 Basic stats: PARTIAL Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 2044 Basic stats: PARTIAL Column stats: PARTIAL
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/15d7d6dc/ql/src/test/results/clientpositive/llap/insert1_overwrite_partitions.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/insert1_overwrite_partitions.q.out b/ql/src/test/results/clientpositive/llap/insert1_overwrite_partitions.q.out
index 228cb6a..13b435c 100644
--- a/ql/src/test/results/clientpositive/llap/insert1_overwrite_partitions.q.out
+++ b/ql/src/test/results/clientpositive/llap/insert1_overwrite_partitions.q.out
@@ -58,15 +58,15 @@ STAGE PLANS:
TableScan
alias: sourcetable
filterExpr: ((ds = '2011-11-11') and (hr = '11')) (type: boolean)
- Statistics: Num rows: 99 Data size: 93448 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 99 Data size: 93448 Basic stats: PARTIAL Column stats: NONE
Select Operator
expressions: one (type: string), two (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 99 Data size: 93448 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 99 Data size: 93448 Basic stats: PARTIAL Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: --
- Statistics: Num rows: 99 Data size: 93448 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 99 Data size: 93448 Basic stats: PARTIAL Column stats: NONE
Execution mode: vectorized, llap
LLAP IO: no inputs
Reducer 2
@@ -75,13 +75,13 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 99 Data size: 93448 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 99 Data size: 93448 Basic stats: PARTIAL Column stats: NONE
Limit
Number of rows: 5
- Statistics: Num rows: 5 Data size: 4715 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 4715 Basic stats: PARTIAL Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 5 Data size: 4715 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 4715 Basic stats: PARTIAL Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -90,18 +90,18 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string), _col1 (type: string), '2011-11-11' (type: string), '11' (type: string)
outputColumnNames: one, two, ds, hr
- Statistics: Num rows: 5 Data size: 4715 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 4715 Basic stats: PARTIAL Column stats: NONE
Group By Operator
aggregations: compute_stats(one, 'hll'), compute_stats(two, 'hll')
keys: ds (type: string), hr (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 5 Data size: 4715 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 4715 Basic stats: PARTIAL Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 5 Data size: 4715 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 4715 Basic stats: PARTIAL Column stats: NONE
value expressions: _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
Reducer 3
Execution mode: llap
@@ -111,14 +111,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 2 Data size: 1886 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 1886 Basic stats: PARTIAL Column stats: NONE
Select Operator
expressions: _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 2 Data size: 1886 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 1886 Basic stats: PARTIAL Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 2 Data size: 1886 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 1886 Basic stats: PARTIAL Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -247,15 +247,15 @@ STAGE PLANS:
TableScan
alias: sourcetable
filterExpr: ((ds = '2011-11-11') and (hr = '11')) (type: boolean)
- Statistics: Num rows: 99 Data size: 93448 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 99 Data size: 93448 Basic stats: PARTIAL Column stats: NONE
Select Operator
expressions: one (type: string), two (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 99 Data size: 93448 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 99 Data size: 93448 Basic stats: PARTIAL Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: --
- Statistics: Num rows: 99 Data size: 93448 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 99 Data size: 93448 Basic stats: PARTIAL Column stats: NONE
Execution mode: vectorized, llap
LLAP IO: no inputs
Reducer 2
@@ -264,13 +264,13 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 99 Data size: 93448 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 99 Data size: 93448 Basic stats: PARTIAL Column stats: NONE
Limit
Number of rows: 5
- Statistics: Num rows: 5 Data size: 4715 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 4715 Basic stats: PARTIAL Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 5 Data size: 4715 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 4715 Basic stats: PARTIAL Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -279,15 +279,15 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string), _col1 (type: string)
outputColumnNames: one, two
- Statistics: Num rows: 5 Data size: 4715 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 4715 Basic stats: PARTIAL Column stats: NONE
Group By Operator
aggregations: compute_stats(one, 'hll'), compute_stats(two, 'hll')
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1248 Basic stats: PARTIAL Column stats: NONE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 1248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1248 Basic stats: PARTIAL Column stats: NONE
value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
Reducer 3
Execution mode: llap
@@ -296,10 +296,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1248 Basic stats: PARTIAL Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 1248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1248 Basic stats: PARTIAL Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -405,15 +405,15 @@ STAGE PLANS:
TableScan
alias: sourcetable
filterExpr: ((ds = '2011-11-11') and (hr = '11')) (type: boolean)
- Statistics: Num rows: 99 Data size: 93448 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 99 Data size: 93448 Basic stats: PARTIAL Column stats: NONE
Select Operator
expressions: one (type: string), two (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 99 Data size: 93448 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 99 Data size: 93448 Basic stats: PARTIAL Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: --
- Statistics: Num rows: 99 Data size: 93448 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 99 Data size: 93448 Basic stats: PARTIAL Column stats: NONE
Execution mode: vectorized, llap
LLAP IO: no inputs
Reducer 2
@@ -422,13 +422,13 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 99 Data size: 93448 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 99 Data size: 93448 Basic stats: PARTIAL Column stats: NONE
Limit
Number of rows: 5
- Statistics: Num rows: 5 Data size: 4715 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 4715 Basic stats: PARTIAL Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 5 Data size: 4715 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 4715 Basic stats: PARTIAL Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -437,18 +437,18 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string), _col1 (type: string), '2011-11-11' (type: string), '11' (type: string)
outputColumnNames: one, two, ds, hr
- Statistics: Num rows: 5 Data size: 4715 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 4715 Basic stats: PARTIAL Column stats: NONE
Group By Operator
aggregations: compute_stats(one, 'hll'), compute_stats(two, 'hll')
keys: ds (type: string), hr (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 5 Data size: 4715 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 4715 Basic stats: PARTIAL Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 5 Data size: 4715 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 4715 Basic stats: PARTIAL Column stats: NONE
value expressions: _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
Reducer 3
Execution mode: llap
@@ -458,14 +458,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 2 Data size: 1886 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 1886 Basic stats: PARTIAL Column stats: NONE
Select Operator
expressions: _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 2 Data size: 1886 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 1886 Basic stats: PARTIAL Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 2 Data size: 1886 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 1886 Basic stats: PARTIAL 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/15d7d6dc/ql/src/test/results/clientpositive/llap/insert_values_orig_table_use_metadata.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/insert_values_orig_table_use_metadata.q.out b/ql/src/test/results/clientpositive/llap/insert_values_orig_table_use_metadata.q.out
index 8bd95b1..59faeeb 100644
--- a/ql/src/test/results/clientpositive/llap/insert_values_orig_table_use_metadata.q.out
+++ b/ql/src/test/results/clientpositive/llap/insert_values_orig_table_use_metadata.q.out
@@ -907,17 +907,17 @@ STAGE PLANS:
TableScan
alias: sp
filterExpr: ((ds = '2008-04-08') and (hr = '11')) (type: boolean)
- Statistics: Num rows: 99 Data size: 58912 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 99 Data size: 58912 Basic stats: PARTIAL Column stats: COMPLETE
Select Operator
- Statistics: Num rows: 99 Data size: 58912 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 99 Data size: 58912 Basic stats: PARTIAL Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -928,10 +928,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL 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/15d7d6dc/ql/src/test/results/clientpositive/llap/join_reordering_no_stats.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/join_reordering_no_stats.q.out b/ql/src/test/results/clientpositive/llap/join_reordering_no_stats.q.out
index 6c06662..ab17005 100644
--- a/ql/src/test/results/clientpositive/llap/join_reordering_no_stats.q.out
+++ b/ql/src/test/results/clientpositive/llap/join_reordering_no_stats.q.out
@@ -478,19 +478,19 @@ STAGE PLANS:
TableScan
alias: employee_part_n1
filterExpr: employeeid is not null (type: boolean)
- Statistics: Num rows: 8 Data size: 28 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8 Data size: 28 Basic stats: PARTIAL Column stats: NONE
Filter Operator
predicate: employeeid is not null (type: boolean)
- Statistics: Num rows: 6 Data size: 21 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 21 Basic stats: PARTIAL Column stats: NONE
Select Operator
expressions: employeeid (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 21 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 21 Basic stats: PARTIAL Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 6 Data size: 21 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 21 Basic stats: PARTIAL Column stats: NONE
Execution mode: vectorized, llap
LLAP IO: no inputs
Reducer 2
@@ -518,15 +518,15 @@ STAGE PLANS:
keys:
0 _col0 (type: int)
1 _col0 (type: int)
- Statistics: Num rows: 6 Data size: 23 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 23 Basic stats: PARTIAL Column stats: NONE
Group By Operator
aggregations: count()
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: PARTIAL Column stats: NONE
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: PARTIAL Column stats: NONE
value expressions: _col0 (type: bigint)
Reducer 4
Execution mode: vectorized, llap
@@ -535,10 +535,10 @@ STAGE PLANS:
aggregations: count(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: PARTIAL Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -582,51 +582,51 @@ STAGE PLANS:
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
- key expressions: _col1 (type: int)
+ key expressions: _col0 (type: int)
sort order: +
- Map-reduce partition columns: _col1 (type: int)
+ Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int)
+ value expressions: _col1 (type: int)
Execution mode: vectorized, llap
LLAP IO: no inputs
Map 5
Map Operator Tree:
TableScan
- alias: supplier_nostats
- filterExpr: s_suppkey is not null (type: boolean)
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ alias: employee_part_n1
+ filterExpr: employeeid is not null (type: boolean)
+ Statistics: Num rows: 1 Data size: 4 Basic stats: PARTIAL Column stats: NONE
Filter Operator
- predicate: s_suppkey is not null (type: boolean)
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ predicate: employeeid is not null (type: boolean)
+ Statistics: Num rows: 1 Data size: 4 Basic stats: PARTIAL Column stats: NONE
Select Operator
- expressions: s_suppkey (type: int)
+ expressions: employeeid (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 4 Basic stats: PARTIAL Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 4 Basic stats: PARTIAL Column stats: NONE
Execution mode: vectorized, llap
LLAP IO: no inputs
Map 6
Map Operator Tree:
TableScan
- alias: employee_part_n1
- filterExpr: employeeid is not null (type: boolean)
- Statistics: Num rows: 8 Data size: 28 Basic stats: COMPLETE Column stats: NONE
+ alias: supplier_nostats
+ filterExpr: s_suppkey is not null (type: boolean)
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: employeeid is not null (type: boolean)
- Statistics: Num rows: 6 Data size: 21 Basic stats: COMPLETE Column stats: NONE
+ predicate: s_suppkey is not null (type: boolean)
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: employeeid (type: int)
+ expressions: s_suppkey (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 21 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 6 Data size: 21 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized, llap
LLAP IO: no inputs
Reducer 2
@@ -636,15 +636,15 @@ STAGE PLANS:
condition map:
Inner Join 0 to 1
keys:
- 0 _col1 (type: int)
+ 0 _col0 (type: int)
1 _col0 (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ outputColumnNames: _col1
+ Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE
Reduce Output Operator
- key expressions: _col0 (type: int)
+ key expressions: _col1 (type: int)
sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Map-reduce partition columns: _col1 (type: int)
+ Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE
Reducer 3
Execution mode: llap
Reduce Operator Tree:
@@ -652,17 +652,17 @@ STAGE PLANS:
condition map:
Inner Join 0 to 1
keys:
- 0 _col0 (type: int)
+ 0 _col1 (type: int)
1 _col0 (type: int)
- Statistics: Num rows: 6 Data size: 23 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE
Group By Operator
aggregations: count()
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: PARTIAL Column stats: NONE
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: PARTIAL Column stats: NONE
value expressions: _col0 (type: bigint)
Reducer 4
Execution mode: vectorized, llap
@@ -671,10 +671,10 @@ STAGE PLANS:
aggregations: count(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: PARTIAL Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL 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/15d7d6dc/ql/src/test/results/clientpositive/llap/stats11.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/stats11.q.out b/ql/src/test/results/clientpositive/llap/stats11.q.out
index 4fd749d..e2e7228 100644
--- a/ql/src/test/results/clientpositive/llap/stats11.q.out
+++ b/ql/src/test/results/clientpositive/llap/stats11.q.out
@@ -394,22 +394,22 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 149 Data size: 85004 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 149 Data size: 85004 Basic stats: PARTIAL Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: key is not null (type: boolean)
- Statistics: Num rows: 142 Data size: 81010 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 142 Data size: 81010 Basic stats: PARTIAL Column stats: NONE
Select Operator
expressions: key (type: int), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 142 Data size: 81010 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 142 Data size: 81010 Basic stats: PARTIAL Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
null sort order: a
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 142 Data size: 81010 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 142 Data size: 81010 Basic stats: PARTIAL Column stats: NONE
tag: 1
value expressions: _col1 (type: string)
auto parallelism: true
@@ -481,17 +481,17 @@ STAGE PLANS:
1 _col0 (type: int)
outputColumnNames: _col0, _col1, _col3
Position of Big Table: 1
- Statistics: Num rows: 156 Data size: 89111 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 156 Data size: 89111 Basic stats: PARTIAL Column stats: NONE
Select Operator
expressions: UDFToString(_col0) (type: string), _col1 (type: string), _col3 (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 156 Data size: 89111 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 156 Data size: 89111 Basic stats: PARTIAL Column stats: NONE
File Output Operator
compressed: false
GlobalTableId: 1
#### A masked pattern was here ####
NumFilesPerFileSink: 1
- Statistics: Num rows: 156 Data size: 89111 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 156 Data size: 89111 Basic stats: PARTIAL Column stats: NONE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.TextInputFormat
@@ -522,16 +522,16 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
outputColumnNames: key, value1, value2
- Statistics: Num rows: 156 Data size: 89111 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 156 Data size: 89111 Basic stats: PARTIAL Column stats: NONE
Group By Operator
aggregations: compute_stats(key, 'hll'), compute_stats(value1, 'hll'), compute_stats(value2, 'hll')
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: PARTIAL Column stats: NONE
Reduce Output Operator
null sort order:
sort order:
- Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: PARTIAL Column stats: NONE
tag: -1
value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
auto parallelism: false
@@ -543,13 +543,13 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: PARTIAL Column stats: NONE
File Output Operator
compressed: false
GlobalTableId: 0
#### A masked pattern was here ####
NumFilesPerFileSink: 1
- Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: PARTIAL Column stats: NONE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -821,22 +821,22 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 149 Data size: 85004 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 149 Data size: 85004 Basic stats: PARTIAL Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: key is not null (type: boolean)
- Statistics: Num rows: 142 Data size: 81010 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 142 Data size: 81010 Basic stats: PARTIAL Column stats: NONE
Select Operator
expressions: key (type: int), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 142 Data size: 81010 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 142 Data size: 81010 Basic stats: PARTIAL Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
null sort order: a
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 142 Data size: 81010 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 142 Data size: 81010 Basic stats: PARTIAL Column stats: NONE
tag: 1
value expressions: _col1 (type: string)
auto parallelism: true
@@ -908,17 +908,17 @@ STAGE PLANS:
1 _col0 (type: int)
outputColumnNames: _col0, _col1, _col3
Position of Big Table: 1
- Statistics: Num rows: 156 Data size: 89111 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 156 Data size: 89111 Basic stats: PARTIAL Column stats: NONE
Select Operator
expressions: UDFToString(_col0) (type: string), _col1 (type: string), _col3 (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 156 Data size: 89111 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 156 Data size: 89111 Basic stats: PARTIAL Column stats: NONE
File Output Operator
compressed: false
GlobalTableId: 1
#### A masked pattern was here ####
NumFilesPerFileSink: 1
- Statistics: Num rows: 156 Data size: 89111 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 156 Data size: 89111 Basic stats: PARTIAL Column stats: NONE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.TextInputFormat
@@ -949,16 +949,16 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
outputColumnNames: key, value1, value2
- Statistics: Num rows: 156 Data size: 89111 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 156 Data size: 89111 Basic stats: PARTIAL Column stats: NONE
Group By Operator
aggregations: compute_stats(key, 'hll'), compute_stats(value1, 'hll'), compute_stats(value2, 'hll')
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: PARTIAL Column stats: NONE
Reduce Output Operator
null sort order:
sort order:
- Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: PARTIAL Column stats: NONE
tag: -1
value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
auto parallelism: false
@@ -970,13 +970,13 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: PARTIAL Column stats: NONE
File Output Operator
compressed: false
GlobalTableId: 0
#### A masked pattern was here ####
NumFilesPerFileSink: 1
- Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: PARTIAL Column stats: NONE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat