Skip to content

Commit

Permalink
HIVE-21304: Make bucketing version usage more robust (Zoltan Haindric…
Browse files Browse the repository at this point in the history
…h reviewed by Jesus Camacho Rodriguez)

Signed-off-by: Zoltan Haindrich <zhaindrich@cloudera.com>
  • Loading branch information
kgyrtkirk committed May 4, 2020
1 parent 342f8fb commit c34ee9d
Show file tree
Hide file tree
Showing 368 changed files with 5,956 additions and 701 deletions.
Original file line number Diff line number Diff line change
Expand Up @@ -107,8 +107,10 @@ STAGE PLANS:
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
bucketingVersion: 2
key expressions: _col1 (type: string), _bucket_number (type: string), _col0 (type: int)
null sort order: aaa
numBuckets: 2
sort order: +++
Map-reduce partition columns: _col1 (type: string)
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Expand Down Expand Up @@ -161,6 +163,7 @@ STAGE PLANS:
expressions: KEY._col0 (type: int), KEY._col1 (type: string), KEY._bucket_number (type: string)
outputColumnNames: _col0, _col1, _bucket_number
File Output Operator
bucketingVersion: 2
compressed: false
GlobalTableId: 1
directory: ### BLOBSTORE_STAGING_PATH ###
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -79,6 +79,7 @@ STAGE PLANS:
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
bucketingVersion: 2
compressed: false
GlobalTableId: 1
directory: ### BLOBSTORE_STAGING_PATH ###
Expand Down Expand Up @@ -123,7 +124,9 @@ STAGE PLANS:
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
bucketingVersion: 2
null sort order:
numBuckets: -1
sort order:
Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE
tag: -1
Expand Down Expand Up @@ -178,6 +181,7 @@ STAGE PLANS:
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
bucketingVersion: 2
compressed: false
GlobalTableId: 0
#### A masked pattern was here ####
Expand All @@ -188,6 +192,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
properties:
bucketing_version -1
columns _col0
columns.types struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>
escape.delim \
Expand Down Expand Up @@ -249,6 +254,7 @@ STAGE PLANS:
TableScan
GatherStats: false
File Output Operator
bucketingVersion: 2
compressed: false
GlobalTableId: 0
directory: ### BLOBSTORE_STAGING_PATH ###
Expand Down Expand Up @@ -372,6 +378,7 @@ STAGE PLANS:
TableScan
GatherStats: false
File Output Operator
bucketingVersion: 2
compressed: false
GlobalTableId: 0
directory: ### BLOBSTORE_STAGING_PATH ###
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -90,6 +90,7 @@ STAGE PLANS:
outputColumnNames: _col0, _col1
Statistics: Num rows: 2 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
bucketingVersion: 2
compressed: false
GlobalTableId: 1
directory: ### BLOBSTORE_STAGING_PATH ###
Expand All @@ -100,6 +101,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
bucketing_version -1
columns _col0,_col1
columns.types int:string
serialization.format 1
Expand Down Expand Up @@ -181,6 +183,7 @@ STAGE PLANS:
TableScan
GatherStats: false
File Output Operator
bucketingVersion: -1
compressed: false
GlobalTableId: 0
directory: ### BLOBSTORE_STAGING_PATH ###
Expand All @@ -189,6 +192,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
bucketing_version -1
columns _col0,_col1
columns.types int:string
serialization.format 1
Expand All @@ -206,6 +210,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
bucketing_version -1
columns _col0,_col1
columns.types int:string
serialization.format 1
Expand All @@ -215,6 +220,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
bucketing_version -1
columns _col0,_col1
columns.types int:string
serialization.format 1
Expand All @@ -236,6 +242,7 @@ STAGE PLANS:
TableScan
GatherStats: false
File Output Operator
bucketingVersion: -1
compressed: false
GlobalTableId: 0
directory: ### BLOBSTORE_STAGING_PATH ###
Expand All @@ -244,6 +251,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
bucketing_version -1
columns _col0,_col1
columns.types int:string
serialization.format 1
Expand All @@ -261,6 +269,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
bucketing_version -1
columns _col0,_col1
columns.types int:string
serialization.format 1
Expand All @@ -270,6 +279,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
bucketing_version -1
columns _col0,_col1
columns.types int:string
serialization.format 1
Expand Down Expand Up @@ -327,6 +337,7 @@ STAGE PLANS:
outputColumnNames: _col0
Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
bucketingVersion: 2
compressed: false
GlobalTableId: 1
directory: ### BLOBSTORE_STAGING_PATH ###
Expand All @@ -337,6 +348,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
bucketing_version -1
columns _col0
columns.types int
serialization.format 1
Expand All @@ -350,6 +362,7 @@ STAGE PLANS:
outputColumnNames: _col0
Statistics: Num rows: 2 Data size: 172 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
bucketingVersion: 2
compressed: false
GlobalTableId: 2
directory: ### BLOBSTORE_STAGING_PATH ###
Expand All @@ -360,6 +373,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
bucketing_version -1
columns _col0
columns.types string
serialization.format 1
Expand Down Expand Up @@ -441,6 +455,7 @@ STAGE PLANS:
TableScan
GatherStats: false
File Output Operator
bucketingVersion: -1
compressed: false
GlobalTableId: 0
directory: ### BLOBSTORE_STAGING_PATH ###
Expand All @@ -449,6 +464,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
bucketing_version -1
columns _col0
columns.types int
serialization.format 1
Expand All @@ -466,6 +482,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
bucketing_version -1
columns _col0
columns.types int
serialization.format 1
Expand All @@ -475,6 +492,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
bucketing_version -1
columns _col0
columns.types int
serialization.format 1
Expand All @@ -496,6 +514,7 @@ STAGE PLANS:
TableScan
GatherStats: false
File Output Operator
bucketingVersion: -1
compressed: false
GlobalTableId: 0
directory: ### BLOBSTORE_STAGING_PATH ###
Expand All @@ -504,6 +523,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
bucketing_version -1
columns _col0
columns.types int
serialization.format 1
Expand All @@ -521,6 +541,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
bucketing_version -1
columns _col0
columns.types int
serialization.format 1
Expand All @@ -530,6 +551,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
bucketing_version -1
columns _col0
columns.types int
serialization.format 1
Expand Down Expand Up @@ -561,6 +583,7 @@ STAGE PLANS:
TableScan
GatherStats: false
File Output Operator
bucketingVersion: -1
compressed: false
GlobalTableId: 0
directory: ### BLOBSTORE_STAGING_PATH ###
Expand All @@ -569,6 +592,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
bucketing_version -1
columns _col0
columns.types string
serialization.format 1
Expand All @@ -586,6 +610,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
bucketing_version -1
columns _col0
columns.types string
serialization.format 1
Expand All @@ -595,6 +620,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
bucketing_version -1
columns _col0
columns.types string
serialization.format 1
Expand All @@ -616,6 +642,7 @@ STAGE PLANS:
TableScan
GatherStats: false
File Output Operator
bucketingVersion: -1
compressed: false
GlobalTableId: 0
directory: ### BLOBSTORE_STAGING_PATH ###
Expand All @@ -624,6 +651,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
bucketing_version -1
columns _col0
columns.types string
serialization.format 1
Expand All @@ -641,6 +669,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
bucketing_version -1
columns _col0
columns.types string
serialization.format 1
Expand All @@ -650,6 +679,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
bucketing_version -1
columns _col0
columns.types string
serialization.format 1
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -125,8 +125,10 @@ STAGE PLANS:
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
bucketingVersion: 2
key expressions: _col1 (type: string), _bucket_number (type: string), _col0 (type: int)
null sort order: aaa
numBuckets: 2
sort order: +++
Map-reduce partition columns: _col1 (type: string)
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Expand Down Expand Up @@ -179,6 +181,7 @@ STAGE PLANS:
expressions: KEY._col0 (type: int), KEY._col1 (type: string), KEY._bucket_number (type: string)
outputColumnNames: _col0, _col1, _bucket_number
File Output Operator
bucketingVersion: 2
compressed: false
GlobalTableId: 1
directory: ### BLOBSTORE_STAGING_PATH ###
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -87,6 +87,7 @@ STAGE PLANS:
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
bucketingVersion: 2
compressed: false
GlobalTableId: 1
directory: ### BLOBSTORE_STAGING_PATH ###
Expand Down Expand Up @@ -131,7 +132,9 @@ STAGE PLANS:
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
bucketingVersion: 2
null sort order:
numBuckets: -1
sort order:
Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE
tag: -1
Expand Down Expand Up @@ -186,6 +189,7 @@ STAGE PLANS:
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
bucketingVersion: 2
compressed: false
GlobalTableId: 0
#### A masked pattern was here ####
Expand All @@ -196,6 +200,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
properties:
bucketing_version -1
columns _col0
columns.types struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>
escape.delim \
Expand Down Expand Up @@ -257,6 +262,7 @@ STAGE PLANS:
TableScan
GatherStats: false
File Output Operator
bucketingVersion: 2
compressed: false
GlobalTableId: 0
directory: ### BLOBSTORE_STAGING_PATH ###
Expand Down Expand Up @@ -380,6 +386,7 @@ STAGE PLANS:
TableScan
GatherStats: false
File Output Operator
bucketingVersion: 2
compressed: false
GlobalTableId: 0
directory: ### BLOBSTORE_STAGING_PATH ###
Expand Down
Loading

0 comments on commit c34ee9d

Please sign in to comment.