You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by se...@apache.org on 2018/03/08 21:00:36 UTC
[2/3] hive git commit: HIVE-18571 : stats issues for MM tables;
ACID doesn't check state for CTAS (Sergey Shelukhin, reviewed by
Eugene Koifman)
http://git-wip-us.apache.org/repos/asf/hive/blob/9b36ffa9/ql/src/test/results/clientpositive/llap/acid_bucket_pruning.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/acid_bucket_pruning.q.out b/ql/src/test/results/clientpositive/llap/acid_bucket_pruning.q.out
index 1abd3a2..6a5ace0 100644
--- a/ql/src/test/results/clientpositive/llap/acid_bucket_pruning.q.out
+++ b/ql/src/test/results/clientpositive/llap/acid_bucket_pruning.q.out
@@ -45,22 +45,22 @@ STAGE PLANS:
alias: acidtbldefault
filterExpr: (a = 1) (type: boolean)
buckets included: [1,] of 16
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1765 Data size: 6712 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: (a = 1) (type: boolean)
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 19 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: 1 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 19 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
GlobalTableId: 0
directory: hdfs://### HDFS PATH ###
NumFilesPerFileSink: 1
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 19 Basic stats: COMPLETE Column stats: NONE
Stats Publishing Key Prefix: hdfs://### HDFS PATH ###
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -98,8 +98,6 @@ STAGE PLANS:
location hdfs://### HDFS PATH ###
name default.acidtbldefault
numFiles 17
- numRows 0
- rawDataSize 0
serialization.ddl struct acidtbldefault { i32 a}
serialization.format 1
serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
@@ -122,8 +120,6 @@ STAGE PLANS:
location hdfs://### HDFS PATH ###
name default.acidtbldefault
numFiles 17
- numRows 0
- rawDataSize 0
serialization.ddl struct acidtbldefault { i32 a}
serialization.format 1
serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
http://git-wip-us.apache.org/repos/asf/hive/blob/9b36ffa9/ql/src/test/results/clientpositive/llap/acid_vectorization_original.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/acid_vectorization_original.q.out b/ql/src/test/results/clientpositive/llap/acid_vectorization_original.q.out
index 64e5b17..05d5d0a 100644
--- a/ql/src/test/results/clientpositive/llap/acid_vectorization_original.q.out
+++ b/ql/src/test/results/clientpositive/llap/acid_vectorization_original.q.out
@@ -665,22 +665,22 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: over10k_orc_bucketed
- Statistics: Num rows: 2098 Data size: 622340 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1227 Data size: 702030 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: ROW__ID (type: struct<writeid:bigint,bucketid:int,rowid:bigint>)
outputColumnNames: ROW__ID
- Statistics: Num rows: 2098 Data size: 622340 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1227 Data size: 702030 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
keys: ROW__ID (type: struct<writeid:bigint,bucketid:int,rowid:bigint>)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1049 Data size: 88116 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 613 Data size: 51492 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>)
sort order: +
Map-reduce partition columns: _col0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>)
- Statistics: Num rows: 1049 Data size: 88116 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 613 Data size: 51492 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Execution mode: llap
LLAP IO: may be used (ACID table)
@@ -692,13 +692,13 @@ STAGE PLANS:
keys: KEY._col0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1049 Data size: 88116 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 613 Data size: 51492 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (_col1 > 1L) (type: boolean)
- Statistics: Num rows: 349 Data size: 29316 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 204 Data size: 17136 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 349 Data size: 29316 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 204 Data size: 17136 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/9b36ffa9/ql/src/test/results/clientpositive/llap/default_constraint.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/default_constraint.q.out b/ql/src/test/results/clientpositive/llap/default_constraint.q.out
index 89b1224..72ff7af 100644
--- a/ql/src/test/results/clientpositive/llap/default_constraint.q.out
+++ b/ql/src/test/results/clientpositive/llap/default_constraint.q.out
@@ -1490,8 +1490,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- numFiles 1
- totalSize 1063
+ COLUMN_STATS_ACCURATE {}
transactional true
transactional_properties default
#### A masked pattern was here ####
@@ -1658,9 +1657,8 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
+ COLUMN_STATS_ACCURATE {}
#### A masked pattern was here ####
- numFiles 2
- totalSize 2127
transactional true
transactional_properties default
#### A masked pattern was here ####
@@ -1737,9 +1735,8 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
+ COLUMN_STATS_ACCURATE {}
#### A masked pattern was here ####
- numFiles 2
- totalSize 2127
transactional true
transactional_properties default
#### A masked pattern was here ####
@@ -1913,9 +1910,8 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
+ COLUMN_STATS_ACCURATE {}
#### A masked pattern was here ####
- numFiles 3
- totalSize 3192
transactional true
transactional_properties default
#### A masked pattern was here ####
@@ -1991,9 +1987,8 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
+ COLUMN_STATS_ACCURATE {}
#### A masked pattern was here ####
- numFiles 3
- totalSize 3192
transactional true
transactional_properties default
#### A masked pattern was here ####
@@ -2070,9 +2065,8 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
+ COLUMN_STATS_ACCURATE {}
#### A masked pattern was here ####
- numFiles 3
- totalSize 3192
transactional true
transactional_properties default
#### A masked pattern was here ####
@@ -2644,8 +2638,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- numFiles 1
- totalSize 1063
+ COLUMN_STATS_ACCURATE {}
transactional true
transactional_properties default
#### A masked pattern was here ####
http://git-wip-us.apache.org/repos/asf/hive/blob/9b36ffa9/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 6a97736..97f7cd1 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
@@ -94,19 +94,19 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: acid_part
- Statistics: Num rows: 1600 Data size: 150327 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 158 Data size: 60414 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (key = 'foo') (type: boolean)
- Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1911 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ROW__ID (type: struct<writeid:bigint,bucketid:int,rowid:bigint>)
outputColumnNames: _col0
- Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1911 Basic stats: COMPLETE 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: 469 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1911 Basic stats: COMPLETE Column stats: NONE
Execution mode: llap
LLAP IO: may be used (ACID table)
Reducer 2
@@ -115,10 +115,10 @@ 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: 469 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1911 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1911 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -189,7 +189,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: acid_part
- Statistics: Num rows: 1600 Data size: 444727 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 157 Data size: 102975 Basic stats: COMPLETE Column stats: PARTIAL
Filter Operator
predicate: (key = 'foo') (type: boolean)
Statistics: Num rows: 5 Data size: 1355 Basic stats: COMPLETE Column stats: PARTIAL
@@ -380,19 +380,19 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: acid_part_sdpo
- Statistics: Num rows: 1600 Data size: 150327 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 174 Data size: 66399 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (key = 'foo') (type: boolean)
- Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1908 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ROW__ID (type: struct<writeid:bigint,bucketid:int,rowid:bigint>)
outputColumnNames: _col0
- Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1908 Basic stats: COMPLETE 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: 469 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1908 Basic stats: COMPLETE Column stats: NONE
Execution mode: llap
LLAP IO: may be used (ACID table)
Reducer 2
@@ -401,10 +401,10 @@ 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: 469 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1908 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1908 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -475,7 +475,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: acid_part_sdpo
- Statistics: Num rows: 1600 Data size: 444727 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 169 Data size: 110820 Basic stats: COMPLETE Column stats: PARTIAL
Filter Operator
predicate: (key = 'foo') (type: boolean)
Statistics: Num rows: 5 Data size: 1355 Basic stats: COMPLETE Column stats: PARTIAL
@@ -675,19 +675,19 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: acid_2l_part
- Statistics: Num rows: 1600 Data size: 150327 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 154 Data size: 59496 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (key = 'foo') (type: boolean)
- Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1931 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ROW__ID (type: struct<writeid:bigint,bucketid:int,rowid:bigint>)
outputColumnNames: _col0
- Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1931 Basic stats: COMPLETE 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: 469 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1931 Basic stats: COMPLETE Column stats: NONE
Execution mode: llap
LLAP IO: may be used (ACID table)
Reducer 2
@@ -696,10 +696,10 @@ 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: 469 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1931 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1931 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -771,19 +771,19 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: acid_2l_part
- Statistics: Num rows: 3200 Data size: 313367 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1600 Data size: 156727 Basic stats: PARTIAL Column stats: PARTIAL
Filter Operator
predicate: (key = 'foo') (type: boolean)
- Statistics: Num rows: 5 Data size: 455 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 489 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: 1740 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 489 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: 1740 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 489 Basic stats: PARTIAL Column stats: PARTIAL
value expressions: _col4 (type: int)
Execution mode: llap
LLAP IO: may be used (ACID table)
@@ -793,10 +793,10 @@ 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: 1740 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 489 Basic stats: PARTIAL Column stats: PARTIAL
File Output Operator
compressed: false
- Statistics: Num rows: 5 Data size: 1740 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 489 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
@@ -897,7 +897,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: acid_2l_part
- Statistics: Num rows: 3200 Data size: 902167 Basic stats: PARTIAL Column stats: PARTIAL
+ Statistics: Num rows: 1600 Data size: 451127 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
@@ -1095,19 +1095,19 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: acid_2l_part_sdpo
- Statistics: Num rows: 1600 Data size: 150327 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 154 Data size: 59496 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (key = 'foo') (type: boolean)
- Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1931 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ROW__ID (type: struct<writeid:bigint,bucketid:int,rowid:bigint>)
outputColumnNames: _col0
- Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1931 Basic stats: COMPLETE 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: 469 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1931 Basic stats: COMPLETE Column stats: NONE
Execution mode: llap
LLAP IO: may be used (ACID table)
Reducer 2
@@ -1116,10 +1116,10 @@ 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: 469 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1931 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1931 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -1191,19 +1191,19 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: acid_2l_part_sdpo
- Statistics: Num rows: 3200 Data size: 313367 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1600 Data size: 156727 Basic stats: PARTIAL Column stats: PARTIAL
Filter Operator
predicate: (key = 'foo') (type: boolean)
- Statistics: Num rows: 5 Data size: 455 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 489 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: 1740 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 489 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: 1740 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 489 Basic stats: PARTIAL Column stats: PARTIAL
Execution mode: llap
LLAP IO: may be used (ACID table)
Reducer 2
@@ -1212,11 +1212,11 @@ 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: 1360 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 489 Basic stats: PARTIAL Column stats: PARTIAL
File Output Operator
compressed: false
Dp Sort State: PARTITION_BUCKET_SORTED
- Statistics: Num rows: 5 Data size: 1360 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 489 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
@@ -1317,7 +1317,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: acid_2l_part_sdpo
- Statistics: Num rows: 3200 Data size: 902167 Basic stats: PARTIAL Column stats: PARTIAL
+ Statistics: Num rows: 1600 Data size: 451127 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
@@ -1515,7 +1515,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: acid_2l_part_sdpo_no_cp
- Statistics: Num rows: 1600 Data size: 598664 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 95 Data size: 81408 Basic stats: COMPLETE Column stats: PARTIAL
Filter Operator
predicate: (key = 'foo') (type: boolean)
Statistics: Num rows: 5 Data size: 1860 Basic stats: COMPLETE Column stats: PARTIAL
@@ -1613,19 +1613,19 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: acid_2l_part_sdpo_no_cp
- Statistics: Num rows: 3200 Data size: 1197144 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1600 Data size: 598664 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: 1870 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: 1870 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: 1870 Basic stats: PARTIAL Column stats: PARTIAL
value expressions: _col1 (type: string), 'bar' (type: string)
Execution mode: llap
LLAP IO: may be used (ACID table)
@@ -1635,11 +1635,11 @@ 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: 1870 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: 1870 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/9b36ffa9/ql/src/test/results/clientpositive/llap/enforce_constraint_notnull.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/enforce_constraint_notnull.q.out b/ql/src/test/results/clientpositive/llap/enforce_constraint_notnull.q.out
index 352f6ba..eeb6a7a 100644
--- a/ql/src/test/results/clientpositive/llap/enforce_constraint_notnull.q.out
+++ b/ql/src/test/results/clientpositive/llap/enforce_constraint_notnull.q.out
@@ -3233,19 +3233,19 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: acid_uami
- Statistics: Num rows: 1 Data size: 328 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 239 Data size: 75112 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (((de = 109.23) or (de = 119.23)) and enforce_constraint(vc is not null)) (type: boolean)
- Statistics: Num rows: 1 Data size: 328 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1571 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ROW__ID (type: struct<writeid:bigint,bucketid:int,rowid:bigint>), i (type: int), vc (type: varchar(128))
outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 1 Data size: 328 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1571 Basic stats: COMPLETE 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: 1 Data size: 328 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1571 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: int), _col3 (type: varchar(128))
Execution mode: llap
LLAP IO: may be used (ACID table)
@@ -3255,10 +3255,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>), VALUE._col0 (type: int), 3.14 (type: decimal(5,2)), VALUE._col1 (type: varchar(128))
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 328 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1571 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 328 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1571 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -3326,19 +3326,19 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: acid_uami
- Statistics: Num rows: 1 Data size: 328 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 277 Data size: 86920 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: ((de = 3.14) and enforce_constraint(i is not null) and enforce_constraint(vc is not null)) (type: boolean)
- Statistics: Num rows: 1 Data size: 328 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 313 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ROW__ID (type: struct<writeid:bigint,bucketid:int,rowid:bigint>), i (type: int), vc (type: varchar(128))
outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 1 Data size: 328 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 313 Basic stats: COMPLETE 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: 1 Data size: 328 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 313 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: int), _col3 (type: varchar(128))
Execution mode: llap
LLAP IO: may be used (ACID table)
@@ -3348,10 +3348,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>), VALUE._col0 (type: int), 3.14 (type: decimal(5,2)), VALUE._col1 (type: varchar(128))
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 328 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 313 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 328 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 313 Basic stats: COMPLETE Column stats: NONE
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/9b36ffa9/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_3.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_3.q.out
index d8863a2..1ef7b87 100644
--- a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_3.q.out
+++ b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_3.q.out
@@ -704,19 +704,19 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: cmv_basetable_2
- Statistics: Num rows: 3 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 42 Data size: 4872 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((c > 10.1) and a is not null) (type: boolean)
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 14 Data size: 1624 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: a (type: int), c (type: decimal(10,2))
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 14 Data size: 1624 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 14 Data size: 1624 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: decimal(10,2))
Execution mode: llap
LLAP IO: may be used (ACID table)
@@ -730,7 +730,7 @@ STAGE PLANS:
0 _col0 (type: int)
1 _col0 (type: int)
outputColumnNames: _col0, _col2
- Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 23 Data size: 2668 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int), _col2 (type: decimal(10,2))
mode: hash
@@ -982,19 +982,19 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: cmv_basetable_2
- Statistics: Num rows: 3 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 42 Data size: 4872 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((c > 10.1) and a is not null) (type: boolean)
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 14 Data size: 1624 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: a (type: int), c (type: decimal(10,2))
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 14 Data size: 1624 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 14 Data size: 1624 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: decimal(10,2))
Execution mode: llap
LLAP IO: may be used (ACID table)
@@ -1008,7 +1008,7 @@ STAGE PLANS:
0 _col0 (type: int)
1 _col0 (type: int)
outputColumnNames: _col0, _col2
- Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 23 Data size: 2668 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int), _col2 (type: decimal(10,2))
mode: hash
http://git-wip-us.apache.org/repos/asf/hive/blob/9b36ffa9/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_rebuild_dummy.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_rebuild_dummy.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_rebuild_dummy.q.out
index d8863a2..1ef7b87 100644
--- a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_rebuild_dummy.q.out
+++ b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_rebuild_dummy.q.out
@@ -704,19 +704,19 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: cmv_basetable_2
- Statistics: Num rows: 3 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 42 Data size: 4872 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((c > 10.1) and a is not null) (type: boolean)
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 14 Data size: 1624 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: a (type: int), c (type: decimal(10,2))
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 14 Data size: 1624 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 14 Data size: 1624 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: decimal(10,2))
Execution mode: llap
LLAP IO: may be used (ACID table)
@@ -730,7 +730,7 @@ STAGE PLANS:
0 _col0 (type: int)
1 _col0 (type: int)
outputColumnNames: _col0, _col2
- Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 23 Data size: 2668 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int), _col2 (type: decimal(10,2))
mode: hash
@@ -982,19 +982,19 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: cmv_basetable_2
- Statistics: Num rows: 3 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 42 Data size: 4872 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((c > 10.1) and a is not null) (type: boolean)
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 14 Data size: 1624 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: a (type: int), c (type: decimal(10,2))
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 14 Data size: 1624 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 14 Data size: 1624 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: decimal(10,2))
Execution mode: llap
LLAP IO: may be used (ACID table)
@@ -1008,7 +1008,7 @@ STAGE PLANS:
0 _col0 (type: int)
1 _col0 (type: int)
outputColumnNames: _col0, _col2
- Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 23 Data size: 2668 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int), _col2 (type: decimal(10,2))
mode: hash
http://git-wip-us.apache.org/repos/asf/hive/blob/9b36ffa9/ql/src/test/results/clientpositive/llap/mm_all.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/mm_all.q.out b/ql/src/test/results/clientpositive/llap/mm_all.q.out
index 23e733b..7c8a38f 100644
--- a/ql/src/test/results/clientpositive/llap/mm_all.q.out
+++ b/ql/src/test/results/clientpositive/llap/mm_all.q.out
@@ -1623,10 +1623,10 @@ POSTHOOK: Output: default@multi1_mm@p=1
POSTHOOK: Output: default@multi1_mm@p=455
POSTHOOK: Output: default@multi1_mm@p=456
POSTHOOK: Output: default@multi1_mm@p=457
-POSTHOOK: Lineage: multi1_mm PARTITION(p=1).key SIMPLE [(intermediate)intermediate.FieldSchema(name:p, type:int, comment:null), ]
-POSTHOOK: Lineage: multi1_mm PARTITION(p=1).key2 SIMPLE [(intermediate)intermediate.FieldSchema(name:key, type:int, comment:null), ]
POSTHOOK: Lineage: multi1_mm PARTITION(p=1).key SIMPLE [(intermediate)intermediate.FieldSchema(name:key, type:int, comment:null), ]
POSTHOOK: Lineage: multi1_mm PARTITION(p=1).key2 SIMPLE [(intermediate)intermediate.FieldSchema(name:p, type:int, comment:null), ]
+POSTHOOK: Lineage: multi1_mm PARTITION(p=1).key SIMPLE [(intermediate)intermediate.FieldSchema(name:p, type:int, comment:null), ]
+POSTHOOK: Lineage: multi1_mm PARTITION(p=1).key2 SIMPLE [(intermediate)intermediate.FieldSchema(name:key, type:int, comment:null), ]
POSTHOOK: Lineage: multi1_mm PARTITION(p=455).key SIMPLE [(intermediate)intermediate.FieldSchema(name:p, type:int, comment:null), ]
POSTHOOK: Lineage: multi1_mm PARTITION(p=455).key2 SIMPLE [(intermediate)intermediate.FieldSchema(name:key, type:int, comment:null), ]
POSTHOOK: Lineage: multi1_mm PARTITION(p=456).key SIMPLE [(intermediate)intermediate.FieldSchema(name:p, type:int, comment:null), ]
@@ -1700,10 +1700,10 @@ POSTHOOK: Input: default@intermediate@p=455
POSTHOOK: Input: default@intermediate@p=456
POSTHOOK: Input: default@intermediate@p=457
POSTHOOK: Output: default@multi1_mm@p=1
-POSTHOOK: Lineage: multi1_mm PARTITION(p=1).key SIMPLE [(intermediate)intermediate.FieldSchema(name:key, type:int, comment:null), ]
-POSTHOOK: Lineage: multi1_mm PARTITION(p=1).key2 SIMPLE [(intermediate)intermediate.FieldSchema(name:p, type:int, comment:null), ]
POSTHOOK: Lineage: multi1_mm PARTITION(p=1).key SIMPLE [(intermediate)intermediate.FieldSchema(name:p, type:int, comment:null), ]
POSTHOOK: Lineage: multi1_mm PARTITION(p=1).key2 SIMPLE [(intermediate)intermediate.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: multi1_mm PARTITION(p=1).key SIMPLE [(intermediate)intermediate.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: multi1_mm PARTITION(p=1).key2 SIMPLE [(intermediate)intermediate.FieldSchema(name:p, type:int, comment:null), ]
PREHOOK: query: select key, key2, p from multi1_mm order by key, key2, p
PREHOOK: type: QUERY
PREHOOK: Input: default@multi1_mm
@@ -1815,7 +1815,6 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\"}}
numFiles 3
numRows 6
rawDataSize 13
@@ -1865,7 +1864,6 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\"}}
numFiles 6
numRows 12
rawDataSize 26
@@ -1923,7 +1921,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {}
numFiles 55
numRows 500
rawDataSize 5312
http://git-wip-us.apache.org/repos/asf/hive/blob/9b36ffa9/ql/src/test/results/clientpositive/materialized_view_create_rewrite_3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/materialized_view_create_rewrite_3.q.out b/ql/src/test/results/clientpositive/materialized_view_create_rewrite_3.q.out
index 29e408c..6561456 100644
--- a/ql/src/test/results/clientpositive/materialized_view_create_rewrite_3.q.out
+++ b/ql/src/test/results/clientpositive/materialized_view_create_rewrite_3.q.out
@@ -710,19 +710,19 @@ STAGE PLANS:
Statistics: Num rows: 5 Data size: 1205 Basic stats: COMPLETE Column stats: NONE
TableScan
alias: cmv_basetable_2
- Statistics: Num rows: 3 Data size: 727 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 42 Data size: 23560 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: ((c > 10.1) and a is not null) (type: boolean)
- Statistics: Num rows: 1 Data size: 242 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 14 Data size: 7853 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: a (type: int), c (type: decimal(10,2))
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 242 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 14 Data size: 7853 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: 1 Data size: 242 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 14 Data size: 7853 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: decimal(10,2))
Reduce Operator Tree:
Join Operator
@@ -732,12 +732,12 @@ STAGE PLANS:
0 _col0 (type: int)
1 _col0 (type: int)
outputColumnNames: _col0, _col2
- Statistics: Num rows: 5 Data size: 1325 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 8638 Basic stats: COMPLETE Column stats: NONE
Group By Operator
keys: _col0 (type: int), _col2 (type: decimal(10,2))
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 5 Data size: 1325 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 8638 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -753,20 +753,20 @@ STAGE PLANS:
key expressions: _col0 (type: int), _col1 (type: decimal(10,2))
sort order: ++
Map-reduce partition columns: _col0 (type: int), _col1 (type: decimal(10,2))
- Statistics: Num rows: 5 Data size: 1325 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 8638 Basic stats: COMPLETE Column stats: NONE
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: int), KEY._col1 (type: decimal(10,2))
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 4031 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 4031 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 4031 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1013,19 +1013,19 @@ STAGE PLANS:
Statistics: Num rows: 5 Data size: 1205 Basic stats: COMPLETE Column stats: NONE
TableScan
alias: cmv_basetable_2
- Statistics: Num rows: 3 Data size: 727 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 42 Data size: 23560 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: ((c > 10.1) and a is not null) (type: boolean)
- Statistics: Num rows: 1 Data size: 242 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 14 Data size: 7853 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: a (type: int), c (type: decimal(10,2))
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 242 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 14 Data size: 7853 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: 1 Data size: 242 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 14 Data size: 7853 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: decimal(10,2))
Reduce Operator Tree:
Join Operator
@@ -1035,12 +1035,12 @@ STAGE PLANS:
0 _col0 (type: int)
1 _col0 (type: int)
outputColumnNames: _col0, _col2
- Statistics: Num rows: 5 Data size: 1325 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 8638 Basic stats: COMPLETE Column stats: NONE
Group By Operator
keys: _col0 (type: int), _col2 (type: decimal(10,2))
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 5 Data size: 1325 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 8638 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -1056,20 +1056,20 @@ STAGE PLANS:
key expressions: _col0 (type: int), _col1 (type: decimal(10,2))
sort order: ++
Map-reduce partition columns: _col0 (type: int), _col1 (type: decimal(10,2))
- Statistics: Num rows: 5 Data size: 1325 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 8638 Basic stats: COMPLETE Column stats: NONE
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: int), KEY._col1 (type: decimal(10,2))
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 4031 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 4031 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 4031 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/9b36ffa9/ql/src/test/results/clientpositive/mm_all.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/mm_all.q.out b/ql/src/test/results/clientpositive/mm_all.q.out
index ac6c080..a0cbdb5 100644
--- a/ql/src/test/results/clientpositive/mm_all.q.out
+++ b/ql/src/test/results/clientpositive/mm_all.q.out
@@ -1637,10 +1637,10 @@ POSTHOOK: Output: default@multi1_mm@p=1
POSTHOOK: Output: default@multi1_mm@p=455
POSTHOOK: Output: default@multi1_mm@p=456
POSTHOOK: Output: default@multi1_mm@p=457
-POSTHOOK: Lineage: multi1_mm PARTITION(p=1).key SIMPLE [(intermediate)intermediate.FieldSchema(name:p, type:int, comment:null), ]
-POSTHOOK: Lineage: multi1_mm PARTITION(p=1).key2 SIMPLE [(intermediate)intermediate.FieldSchema(name:key, type:int, comment:null), ]
POSTHOOK: Lineage: multi1_mm PARTITION(p=1).key SIMPLE [(intermediate)intermediate.FieldSchema(name:key, type:int, comment:null), ]
POSTHOOK: Lineage: multi1_mm PARTITION(p=1).key2 SIMPLE [(intermediate)intermediate.FieldSchema(name:p, type:int, comment:null), ]
+POSTHOOK: Lineage: multi1_mm PARTITION(p=1).key SIMPLE [(intermediate)intermediate.FieldSchema(name:p, type:int, comment:null), ]
+POSTHOOK: Lineage: multi1_mm PARTITION(p=1).key2 SIMPLE [(intermediate)intermediate.FieldSchema(name:key, type:int, comment:null), ]
POSTHOOK: Lineage: multi1_mm PARTITION(p=455).key SIMPLE [(intermediate)intermediate.FieldSchema(name:p, type:int, comment:null), ]
POSTHOOK: Lineage: multi1_mm PARTITION(p=455).key2 SIMPLE [(intermediate)intermediate.FieldSchema(name:key, type:int, comment:null), ]
POSTHOOK: Lineage: multi1_mm PARTITION(p=456).key SIMPLE [(intermediate)intermediate.FieldSchema(name:p, type:int, comment:null), ]
@@ -1829,7 +1829,6 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\"}}
numFiles 1
numRows 6
rawDataSize 13
@@ -1879,7 +1878,6 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\"}}
numFiles 2
numRows 12
rawDataSize 26
@@ -1937,7 +1935,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {}
numFiles 1
numRows 500
rawDataSize 5312
http://git-wip-us.apache.org/repos/asf/hive/blob/9b36ffa9/ql/src/test/results/clientpositive/mm_default.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/mm_default.q.out b/ql/src/test/results/clientpositive/mm_default.q.out
index 1345efd..f5341ed 100644
--- a/ql/src/test/results/clientpositive/mm_default.q.out
+++ b/ql/src/test/results/clientpositive/mm_default.q.out
@@ -180,7 +180,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {}
numFiles 1
numRows 1
rawDataSize 3
http://git-wip-us.apache.org/repos/asf/hive/blob/9b36ffa9/ql/src/test/results/clientpositive/tez/acid_vectorization_original_tez.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/acid_vectorization_original_tez.q.out b/ql/src/test/results/clientpositive/tez/acid_vectorization_original_tez.q.out
index 92a04dd..114f9a8 100644
--- a/ql/src/test/results/clientpositive/tez/acid_vectorization_original_tez.q.out
+++ b/ql/src/test/results/clientpositive/tez/acid_vectorization_original_tez.q.out
@@ -680,22 +680,22 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: over10k_orc_bucketed
- Statistics: Num rows: 2098 Data size: 622340 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1227 Data size: 702030 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: ROW__ID (type: struct<writeid:bigint,bucketid:int,rowid:bigint>)
outputColumnNames: ROW__ID
- Statistics: Num rows: 2098 Data size: 622340 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1227 Data size: 702030 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
keys: ROW__ID (type: struct<writeid:bigint,bucketid:int,rowid:bigint>)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1049 Data size: 88116 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 613 Data size: 51492 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>)
sort order: +
Map-reduce partition columns: _col0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>)
- Statistics: Num rows: 1049 Data size: 88116 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 613 Data size: 51492 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Reducer 2
Reduce Operator Tree:
@@ -704,13 +704,13 @@ STAGE PLANS:
keys: KEY._col0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1049 Data size: 88116 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 613 Data size: 51492 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (_col1 > 1L) (type: boolean)
- Statistics: Num rows: 349 Data size: 29316 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 204 Data size: 17136 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 349 Data size: 29316 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 204 Data size: 17136 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/9b36ffa9/ql/src/test/results/clientpositive/tez/explainanalyze_5.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/explainanalyze_5.q.out b/ql/src/test/results/clientpositive/tez/explainanalyze_5.q.out
index 7f18f2b..8d67fe4 100644
--- a/ql/src/test/results/clientpositive/tez/explainanalyze_5.q.out
+++ b/ql/src/test/results/clientpositive/tez/explainanalyze_5.q.out
@@ -295,16 +295,16 @@ Stage-3
Reducer 2
File Output Operator [FS_8]
table:{"name:":"default.acid_uami"}
- Select Operator [SEL_4] (rows=1/2 width=328)
+ Select Operator [SEL_4] (rows=10/2 width=321)
Output:["_col0","_col1","_col2","_col3"]
<-Map 1 [SIMPLE_EDGE]
SHUFFLE [RS_3]
PartitionCols:UDFToInteger(_col0)
- Select Operator [SEL_2] (rows=1/2 width=328)
+ Select Operator [SEL_2] (rows=10/2 width=321)
Output:["_col0","_col1","_col3"]
- Filter Operator [FIL_9] (rows=1/2 width=328)
+ Filter Operator [FIL_9] (rows=10/2 width=321)
predicate:((de = 109.23) or (de = 119.23))
- TableScan [TS_0] (rows=1/4 width=328)
+ TableScan [TS_0] (rows=49/4 width=321)
default@acid_uami,acid_uami, ACID table,Tbl:COMPLETE,Col:NONE,Output:["i","de","vc"]
PREHOOK: query: select * from acid_uami order by de
http://git-wip-us.apache.org/repos/asf/hive/blob/9b36ffa9/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/StatsSetupConst.java
----------------------------------------------------------------------
diff --git a/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/StatsSetupConst.java b/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/StatsSetupConst.java
index 5919089..78ea01d 100644
--- a/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/StatsSetupConst.java
+++ b/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/StatsSetupConst.java
@@ -270,6 +270,7 @@ public class StatsSetupConst {
if (params == null) {
return;
}
+
ColumnStatsAccurate stats = parseStatsAcc(params.get(COLUMN_STATS_ACCURATE));
stats.columnStats.clear();
http://git-wip-us.apache.org/repos/asf/hive/blob/9b36ffa9/standalone-metastore/src/main/java/org/apache/hadoop/hive/metastore/HiveAlterHandler.java
----------------------------------------------------------------------
diff --git a/standalone-metastore/src/main/java/org/apache/hadoop/hive/metastore/HiveAlterHandler.java b/standalone-metastore/src/main/java/org/apache/hadoop/hive/metastore/HiveAlterHandler.java
index 89354a2..0dd3eb1 100644
--- a/standalone-metastore/src/main/java/org/apache/hadoop/hive/metastore/HiveAlterHandler.java
+++ b/standalone-metastore/src/main/java/org/apache/hadoop/hive/metastore/HiveAlterHandler.java
@@ -297,7 +297,7 @@ public class HiveAlterHandler implements AlterHandler {
!isPartitionedTable) {
Database db = msdb.getDatabase(newDbName);
// Update table stats. For partitioned table, we update stats in alterPartition()
- MetaStoreUtils.updateTableStatsFast(db, newt, wh, false, true, environmentContext);
+ MetaStoreUtils.updateTableStatsFast(db, newt, wh, false, true, environmentContext, false);
}
if (isPartitionedTable) {
@@ -436,23 +436,25 @@ public class HiveAlterHandler implements AlterHandler {
.currentTimeMillis() / 1000));
}
- Table tbl = msdb.getTable(dbname, name);
- if (tbl == null) {
- throw new InvalidObjectException(
- "Unable to alter partition because table or database does not exist.");
- }
//alter partition
if (part_vals == null || part_vals.size() == 0) {
try {
msdb.openTransaction();
+
+ Table tbl = msdb.getTable(dbname, name);
+ if (tbl == null) {
+ throw new InvalidObjectException(
+ "Unable to alter partition because table or database does not exist.");
+ }
oldPart = msdb.getPartition(dbname, name, new_part.getValues());
if (MetaStoreUtils.requireCalStats(oldPart, new_part, tbl, environmentContext)) {
// if stats are same, no need to update
if (MetaStoreUtils.isFastStatsSame(oldPart, new_part)) {
MetaStoreUtils.updateBasicState(environmentContext, new_part.getParameters());
} else {
- MetaStoreUtils.updatePartitionStatsFast(new_part, wh, false, true, environmentContext);
+ MetaStoreUtils.updatePartitionStatsFast(
+ new_part, tbl, wh, false, true, environmentContext, false);
}
}
@@ -494,6 +496,11 @@ public class HiveAlterHandler implements AlterHandler {
boolean dataWasMoved = false;
try {
msdb.openTransaction();
+ Table tbl = msdb.getTable(dbname, name);
+ if (tbl == null) {
+ throw new InvalidObjectException(
+ "Unable to alter partition because table or database does not exist.");
+ }
try {
oldPart = msdb.getPartition(dbname, name, part_vals);
} catch (NoSuchObjectException e) {
@@ -581,7 +588,8 @@ public class HiveAlterHandler implements AlterHandler {
}
if (MetaStoreUtils.requireCalStats(oldPart, new_part, tbl, environmentContext)) {
- MetaStoreUtils.updatePartitionStatsFast(new_part, wh, false, true, environmentContext);
+ MetaStoreUtils.updatePartitionStatsFast(
+ new_part, tbl, wh, false, true, environmentContext, false);
}
String newPartName = Warehouse.makePartName(tbl.getPartitionKeys(), new_part.getValues());
@@ -650,15 +658,16 @@ public class HiveAlterHandler implements AlterHandler {
transactionalListeners = handler.getTransactionalListeners();
}
- Table tbl = msdb.getTable(dbname, name);
- if (tbl == null) {
- throw new InvalidObjectException(
- "Unable to alter partitions because table or database does not exist.");
- }
boolean success = false;
try {
msdb.openTransaction();
+
+ Table tbl = msdb.getTable(dbname, name);
+ if (tbl == null) {
+ throw new InvalidObjectException(
+ "Unable to alter partitions because table or database does not exist.");
+ }
for (Partition tmpPart: new_parts) {
// Set DDL time to now if not specified
if (tmpPart.getParameters() == null ||
@@ -677,7 +686,8 @@ public class HiveAlterHandler implements AlterHandler {
if (MetaStoreUtils.isFastStatsSame(oldTmpPart, tmpPart)) {
MetaStoreUtils.updateBasicState(environmentContext, tmpPart.getParameters());
} else {
- MetaStoreUtils.updatePartitionStatsFast(tmpPart, wh, false, true, environmentContext);
+ MetaStoreUtils.updatePartitionStatsFast(
+ tmpPart, tbl, wh, false, true, environmentContext, false);
}
}
http://git-wip-us.apache.org/repos/asf/hive/blob/9b36ffa9/standalone-metastore/src/main/java/org/apache/hadoop/hive/metastore/HiveMetaStore.java
----------------------------------------------------------------------
diff --git a/standalone-metastore/src/main/java/org/apache/hadoop/hive/metastore/HiveMetaStore.java b/standalone-metastore/src/main/java/org/apache/hadoop/hive/metastore/HiveMetaStore.java
index 662de9a..c99c3af 100644
--- a/standalone-metastore/src/main/java/org/apache/hadoop/hive/metastore/HiveMetaStore.java
+++ b/standalone-metastore/src/main/java/org/apache/hadoop/hive/metastore/HiveMetaStore.java
@@ -1488,7 +1488,7 @@ public class HiveMetaStore extends ThriftHiveMetastore {
}
if (MetastoreConf.getBoolVar(conf, ConfVars.STATS_AUTO_GATHER) &&
!MetaStoreUtils.isView(tbl)) {
- MetaStoreUtils.updateTableStatsFast(db, tbl, wh, madeDir, envContext);
+ MetaStoreUtils.updateTableStatsFast(db, tbl, wh, madeDir, false, envContext, true);
}
// set create time
@@ -2673,7 +2673,7 @@ public class HiveMetaStore extends ThriftHiveMetastore {
if (MetastoreConf.getBoolVar(conf, ConfVars.STATS_AUTO_GATHER) &&
!MetaStoreUtils.isView(tbl)) {
- MetaStoreUtils.updatePartitionStatsFast(part, wh, madeDir, envContext);
+ MetaStoreUtils.updatePartitionStatsFast(part, tbl, wh, madeDir, false, envContext, true);
}
if (ms.addPartition(part)) {
@@ -3241,7 +3241,7 @@ public class HiveMetaStore extends ThriftHiveMetastore {
final Table tbl, final PartitionSpecProxy.PartitionIterator part, boolean madeDir) throws MetaException {
if (MetastoreConf.getBoolVar(conf, ConfVars.STATS_AUTO_GATHER) &&
!MetaStoreUtils.isView(tbl)) {
- MetaStoreUtils.updatePartitionStatsFast(part, wh, madeDir, false, null);
+ MetaStoreUtils.updatePartitionStatsFast(part, tbl, wh, madeDir, false, null, true);
}
// set create time
http://git-wip-us.apache.org/repos/asf/hive/blob/9b36ffa9/standalone-metastore/src/main/java/org/apache/hadoop/hive/metastore/Warehouse.java
----------------------------------------------------------------------
diff --git a/standalone-metastore/src/main/java/org/apache/hadoop/hive/metastore/Warehouse.java b/standalone-metastore/src/main/java/org/apache/hadoop/hive/metastore/Warehouse.java
index 20c1060..445a7b8 100755
--- a/standalone-metastore/src/main/java/org/apache/hadoop/hive/metastore/Warehouse.java
+++ b/standalone-metastore/src/main/java/org/apache/hadoop/hive/metastore/Warehouse.java
@@ -543,7 +543,7 @@ public class Warehouse {
* @return array of FileStatus objects corresponding to the files
* making up the passed storage description
*/
- public FileStatus[] getFileStatusesForSD(StorageDescriptor desc)
+ public List<FileStatus> getFileStatusesForSD(StorageDescriptor desc)
throws MetaException {
return getFileStatusesForLocation(desc.getLocation());
}
@@ -553,7 +553,7 @@ public class Warehouse {
* @return array of FileStatus objects corresponding to the files
* making up the passed storage description
*/
- public FileStatus[] getFileStatusesForLocation(String location)
+ public List<FileStatus> getFileStatusesForLocation(String location)
throws MetaException {
try {
Path path = new Path(location);
@@ -571,7 +571,7 @@ public class Warehouse {
* @return array of FileStatus objects corresponding to the files making up the passed
* unpartitioned table
*/
- public FileStatus[] getFileStatusesForUnpartitionedTable(Database db, Table table)
+ public List<FileStatus> getFileStatusesForUnpartitionedTable(Database db, Table table)
throws MetaException {
Path tablePath = getDnsPath(new Path(table.getSd().getLocation()));
try {
http://git-wip-us.apache.org/repos/asf/hive/blob/9b36ffa9/standalone-metastore/src/main/java/org/apache/hadoop/hive/metastore/utils/FileUtils.java
----------------------------------------------------------------------
diff --git a/standalone-metastore/src/main/java/org/apache/hadoop/hive/metastore/utils/FileUtils.java b/standalone-metastore/src/main/java/org/apache/hadoop/hive/metastore/utils/FileUtils.java
index b44ff8c..4138fa5 100644
--- a/standalone-metastore/src/main/java/org/apache/hadoop/hive/metastore/utils/FileUtils.java
+++ b/standalone-metastore/src/main/java/org/apache/hadoop/hive/metastore/utils/FileUtils.java
@@ -17,6 +17,7 @@
*/
package org.apache.hadoop.hive.metastore.utils;
+import org.apache.curator.shaded.com.google.common.collect.Lists;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.ContentSummary;
import org.apache.hadoop.fs.FileStatus;
@@ -314,11 +315,11 @@ public class FileUtils {
* @return array of FileStatus
* @throws IOException
*/
- public static FileStatus[] getFileStatusRecurse(Path path, int level, FileSystem fs)
+ public static List<FileStatus> getFileStatusRecurse(Path path, int level, FileSystem fs)
throws IOException {
// if level is <0, the return all files/directories under the specified path
- if ( level < 0) {
+ if (level < 0) {
List<FileStatus> result = new ArrayList<>();
try {
FileStatus fileStatus = fs.getFileStatus(path);
@@ -328,9 +329,9 @@ public class FileUtils {
// does not exist. But getFileStatus() throw IOException. To mimic the
// similar behavior we will return empty array on exception. For external
// tables, the path of the table will not exists during table creation
- return new FileStatus[0];
+ return new ArrayList<>(0);
}
- return result.toArray(new FileStatus[result.size()]);
+ return result;
}
// construct a path pattern (e.g., /*/*) to find all dynamically generated paths
@@ -339,7 +340,7 @@ public class FileUtils {
sb.append(Path.SEPARATOR).append("*");
}
Path pathPattern = new Path(path, sb.toString());
- return fs.globStatus(pathPattern, FileUtils.HIDDEN_FILES_PATH_FILTER);
+ return Lists.newArrayList(fs.globStatus(pathPattern, FileUtils.HIDDEN_FILES_PATH_FILTER));
}
/**